From 94d8ea4339d99bcebfeaad56629dadf7aa302d29 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Thu, 5 Dec 2024 12:11:17 +0100
Subject: [PATCH 01/31] Endpoint to extract audio from brightcove files

---
 .../no/ndla/audioapi/AudioApiProperties.scala |  8 ++
 .../no/ndla/audioapi/ComponentRegistry.scala  | 30 ++++---
 .../controller/TranscriptionController.scala  | 40 +++++++++
 .../service/TranscriptionService.scala        | 90 +++++++++++++++++++
 .../service/TranscriptionServiceTest.scala    |  3 +
 .../no/ndla/common/aws/NdlaS3Client.scala     | 28 ++++++
 .../brightcove/NdlaBrightcoveClient.scala     | 75 ++++++++++++++++
 project/Dependencies.scala                    |  4 +
 project/Module.scala                          |  1 -
 project/audioapi.scala                        |  3 +-
 10 files changed, 269 insertions(+), 13 deletions(-)
 create mode 100644 audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
 create mode 100644 audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
 create mode 100644 audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
 create mode 100644 common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala b/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
index 7a298818a..2b6cdf5d5 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
@@ -9,6 +9,7 @@
 package no.ndla.audioapi
 
 import com.typesafe.scalalogging.StrictLogging
+import no.ndla.common.Environment.prop
 import no.ndla.common.configuration.{BaseProps, HasBaseProps}
 import no.ndla.database.{DatabaseProps, HasDatabaseProps}
 import no.ndla.network.{AuthUser, Domains}
@@ -36,6 +37,13 @@ class AudioApiProperties extends BaseProps with DatabaseProps with StrictLogging
   val StorageName: String           = propOrElse("AUDIO_FILE_S3_BUCKET", s"$Environment.audio.ndla")
   val StorageRegion: Option[String] = propOrNone("AUDIO_FILE_S3_BUCKET_REGION")
 
+  val TranscribeStorageName: String           = propOrElse("TRANSCRIBE_FILE_S3_BUCKET", s"$Environment.transcribe.ndla")
+  val TranscribeStorageRegion: Option[String] = propOrNone("TRANSCRIBE_FILE_S3_BUCKET_REGION")
+
+  val BrightcoveClientId: String     = prop("BRIGHTCOVE_API_CLIENT_ID")
+  val BrightcoveClientSecret: String = prop("BRIGHTCOVE_API_CLIENT_SECRET")
+  val BrightcoveAccountId: String    = prop("BRIGHTCOVE_ACCOUNT")
+
   val SearchServer: String                 = propOrElse("SEARCH_SERVER", "http://search-audio-api.ndla-local")
   val RunWithSignedSearchRequests: Boolean = propOrElse("RUN_WITH_SIGNED_SEARCH_REQUESTS", "true").toBoolean
   val SearchIndex: String                  = propOrElse("SEARCH_INDEX_NAME", "audios")
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala b/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala
index 3684fcee8..56f2049cf 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala
@@ -17,6 +17,7 @@ import no.ndla.audioapi.service.*
 import no.ndla.audioapi.service.search.*
 import no.ndla.common.Clock
 import no.ndla.common.aws.NdlaS3Client
+import no.ndla.common.brightcove.NdlaBrightcoveClient
 import no.ndla.common.configuration.BaseComponentRegistry
 import no.ndla.database.{DBMigrator, DataSource}
 import no.ndla.network.NdlaClient
@@ -38,6 +39,7 @@ class ComponentRegistry(properties: AudioApiProperties)
     with HealthController
     with AudioController
     with SeriesController
+    with TranscriptionController
     with SearchService
     with AudioSearchService
     with SeriesSearchService
@@ -54,7 +56,9 @@ class ComponentRegistry(properties: AudioApiProperties)
     with DBMigrator
     with ErrorHandling
     with SwaggerDocControllerConfig
-    with NdlaS3Client {
+    with NdlaS3Client
+    with TranscriptionService
+    with NdlaBrightcoveClient {
   override val props: AudioApiProperties = properties
   override val migrator: DBMigrator = DBMigrator(
     new V5__AddAgreementToAudio,
@@ -63,7 +67,8 @@ class ComponentRegistry(properties: AudioApiProperties)
   override val dataSource: HikariDataSource = DataSource.getHikariDataSource
   DataSource.connectToDatabase()
 
-  lazy val s3Client = new NdlaS3Client(props.StorageName, props.StorageRegion)
+  lazy val s3Client         = new NdlaS3Client(props.StorageName, props.StorageRegion)
+  lazy val brightcoveClient = new NdlaBrightcoveClient()
 
   lazy val audioRepository  = new AudioRepository
   lazy val seriesRepository = new SeriesRepository
@@ -71,15 +76,17 @@ class ComponentRegistry(properties: AudioApiProperties)
   lazy val ndlaClient                       = new NdlaClient
   lazy val myndlaApiClient: MyNDLAApiClient = new MyNDLAApiClient
 
-  lazy val readService       = new ReadService
-  lazy val writeService      = new WriteService
-  lazy val validationService = new ValidationService
-  lazy val converterService  = new ConverterService
+  lazy val readService          = new ReadService
+  lazy val writeService         = new WriteService
+  lazy val validationService    = new ValidationService
+  lazy val converterService     = new ConverterService
+  lazy val transcriptionService = new TranscriptionService
 
-  lazy val internController   = new InternController
-  lazy val audioApiController = new AudioController
-  lazy val seriesController   = new SeriesController
-  lazy val healthController   = new HealthController
+  lazy val internController        = new InternController
+  lazy val audioApiController      = new AudioController
+  lazy val seriesController        = new SeriesController
+  lazy val healthController        = new HealthController
+  lazy val transcriptionController = new TranscriptionController
 
   var e4sClient: NdlaE4sClient    = Elastic4sClientFactory.getClient(props.SearchServer)
   lazy val searchConverterService = new SearchConverterService
@@ -97,7 +104,8 @@ class ComponentRegistry(properties: AudioApiProperties)
       audioApiController,
       seriesController,
       internController,
-      healthController
+      healthController,
+      transcriptionController
     ),
     SwaggerDocControllerConfig.swaggerInfo
   )
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
new file mode 100644
index 000000000..1b77682c2
--- /dev/null
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -0,0 +1,40 @@
+package no.ndla.audioapi.controller
+
+import no.ndla.audioapi.Props
+import no.ndla.audioapi.service.{ReadService, TranscriptionService}
+import no.ndla.network.tapir.TapirController
+import no.ndla.network.tapir.TapirUtil.errorOutputsFor
+import sttp.tapir.server.ServerEndpoint
+import sttp.tapir.{EndpointInput, endpoint, path, query}
+import sttp.tapir.*
+
+import scala.util.{Failure, Success}
+trait TranscriptionController {
+  this: Props & TapirController & ReadService & TranscriptionService =>
+  val transcriptionController: TranscriptionController
+  class TranscriptionController() extends TapirController {
+    import props.*
+
+    override val serviceName: String         = "transcription"
+    override val prefix: EndpointInput[Unit] = "audio-api" / "v1" / serviceName
+
+    private val videoId  = path[String]("videoId").description("The video id to transcribe")
+    private val language = query[String]("language").description("The language to transcribe the video to")
+
+    def postExtractAudio: ServerEndpoint[Any, Eff] = endpoint.post
+      .summary("Extract audio from video")
+      .description("Extracts audio from a Brightcove video and uploads it to S3.")
+      .in(videoId)
+      .in(language)
+      .errorOut(errorOutputsFor(400, 500))
+      .serverLogicPure { case (videoId, language) =>
+        transcriptionService.extractAudioFromVideo(videoId, language) match {
+          case Success(_)  => Right(())
+          case Failure(ex) => returnLeftError(ex)
+        }
+      }
+
+    override val endpoints: List[ServerEndpoint[Any, Eff]] = List(postExtractAudio)
+  }
+
+}
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
new file mode 100644
index 000000000..a0e1b1274
--- /dev/null
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -0,0 +1,90 @@
+package no.ndla.audioapi.service
+
+import no.ndla.audioapi.Props
+import no.ndla.common.aws.NdlaS3Client
+import no.ndla.common.brightcove.NdlaBrightcoveClient
+import sttp.client3.{HttpURLConnectionBackend, UriContext, asFile, basicRequest}
+import ws.schild.jave.{Encoder, MultimediaObject}
+import ws.schild.jave.encode.{AudioAttributes, EncodingAttributes}
+
+import java.io.File
+import scala.util.{Failure, Success, Try}
+
+trait TranscriptionService {
+  this: NdlaS3Client & Props & NdlaBrightcoveClient =>
+  val transcriptionService: TranscriptionService
+  class TranscriptionService {
+
+    private lazy val s3TranscribeClient = new NdlaS3Client(props.TranscribeStorageName, props.TranscribeStorageRegion)
+
+    def extractAudioFromVideo(videoId: String, language: String): Try[Unit] = {
+      val accountId = props.BrightcoveAccountId
+      val videoUrl = getVideo(accountId, videoId) match {
+        case Right(sources) => sources.head
+        case Left(error)    => throw new RuntimeException(s"Failed to get video sources: $error")
+      }
+      val videoFile = downloadVideo(videoId, videoUrl)
+
+      val audioFile = new File(s"/tmp/audio_${videoId}.mp3")
+
+      val audioAttributes = new AudioAttributes()
+      audioAttributes.setCodec("libmp3lame")
+      audioAttributes.setBitRate(128000)
+      audioAttributes.setChannels(2)
+      audioAttributes.setSamplingRate(44100)
+
+      val encodingAttributes = new EncodingAttributes()
+      encodingAttributes.setOutputFormat("mp3")
+      encodingAttributes.setAudioAttributes(audioAttributes)
+
+      val encoder = new Encoder()
+      Try {
+        encoder.encode(new MultimediaObject(videoFile), audioFile, encodingAttributes)
+      } match {
+        case Success(_) =>
+          val s3Key = s"/audio/$language/${videoId}.mp3"
+          s3TranscribeClient.putObject(s3Key, audioFile, "audio/mpeg") match {
+            case Success(_) =>
+              s3TranscribeClient.deleteObject(videoFile.getName).map(_ => ())
+            case _ =>
+              Failure(new RuntimeException(s"Failed to upload audio file to S3."))
+          }
+        case Failure(exception) => Failure(exception)
+
+      }
+    }
+
+    private def getVideo(accountId: String, videoId: String): Either[String, Vector[String]] = {
+      val clientId     = props.BrightcoveClientId
+      val clientSecret = props.BrightcoveClientSecret
+      val token        = brightcoveClient.getToken(clientId, clientSecret)
+      token match {
+        case Right(bearerToken) =>
+          val cake = brightcoveClient.getVideoSource(accountId, videoId, bearerToken)
+          cake match {
+            case Right(videoSources) =>
+              val mp4Sources = videoSources
+                .filter(source => source.hcursor.get[String]("container").toOption.contains("MP4"))
+                .map(source => source.hcursor.get[String]("src").toOption.getOrElse(""))
+              if (mp4Sources.nonEmpty) Right(mp4Sources)
+              else Left("No MP4 sources found for video.")
+            case Left(error) => Left(s"Failed to get video sources: $error")
+          }
+        case Left(error) =>
+          Left(s"Failed to retrieve bearer token: $error")
+      }
+    }
+
+    private def downloadVideo(videoId: String, videoUrl: String): File = {
+      val videoFile  = new File(s"/tmp/video_$videoId.mp4")
+      val connection = HttpURLConnectionBackend()
+
+      val response = basicRequest.get(uri"$videoUrl").response(asFile(videoFile)).send(connection)
+
+      response.body match {
+        case Right(file) => file
+        case Left(error) => throw new RuntimeException(s"Failed to download video: $error")
+      }
+    }
+  }
+}
diff --git a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
new file mode 100644
index 000000000..c15bf9f21
--- /dev/null
+++ b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
@@ -0,0 +1,3 @@
+package no.ndla.audioapi.service class TranscriptionServiceTest {
+
+}
diff --git a/common/src/main/scala/no/ndla/common/aws/NdlaS3Client.scala b/common/src/main/scala/no/ndla/common/aws/NdlaS3Client.scala
index 8803eb385..f8a7e43a2 100644
--- a/common/src/main/scala/no/ndla/common/aws/NdlaS3Client.scala
+++ b/common/src/main/scala/no/ndla/common/aws/NdlaS3Client.scala
@@ -13,6 +13,7 @@ import software.amazon.awssdk.regions.Region
 import software.amazon.awssdk.services.s3.model.*
 import software.amazon.awssdk.services.s3.{S3Client, S3ClientBuilder}
 
+import java.io.File
 import scala.util.Try
 
 trait NdlaS3Client {
@@ -81,6 +82,33 @@ trait NdlaS3Client {
       )
     }
 
+    def putObject(
+        key: String,
+        file: File,
+        contentType: String,
+        cacheControl: Option[String] = None
+    ): Try[PutObjectResponse] = Try {
+
+      val por = PutObjectRequest
+        .builder()
+        .bucket(bucket)
+        .key(key)
+        .contentLength(file.length())
+        .contentType(contentType)
+
+      val porWithCacheControl = cacheControl match {
+        case Some(value) => por.cacheControl(value)
+        case None        => por
+      }
+
+      val requestBody = RequestBody.fromFile(file)
+
+      client.putObject(
+        porWithCacheControl.build(),
+        requestBody
+      )
+    }
+
     def updateMetadata(key: String, metadata: java.util.Map[String, String]): Try[_] = Try {
       val cor =
         CopyObjectRequest
diff --git a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
new file mode 100644
index 000000000..25b646304
--- /dev/null
+++ b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
@@ -0,0 +1,75 @@
+package no.ndla.common.brightcove
+
+import io.circe.{Decoder, Json}
+import io.circe.generic.codec.DerivedAsObjectCodec.deriveCodec
+import io.circe.generic.semiauto.deriveDecoder
+import io.circe.parser.*
+import sttp.client3.{HttpClientSyncBackend, UriContext, basicRequest}
+
+case class TokenResponse(access_token: String, token_type: String, expires_in: Int)
+case class VideoSource(
+    src: String,
+    `type`: String,
+    container: String,
+    codec: Option[String] = None,
+    encoding_rate: Option[Int] = None,
+    duration: Option[Int] = None,
+    height: Option[Int] = None,
+    width: Option[Int] = None,
+    size: Option[Long] = None,
+    uploaded_at: Option[String] = None,
+    ext_x_version: Option[String] = None,
+    profiles: Option[String] = None,
+    remote: Option[Boolean] = None
+)
+
+trait NdlaBrightcoveClient {
+  val brightcoveClient: NdlaBrightcoveClient
+
+  class NdlaBrightcoveClient {
+    private val authUrl = "https://oauth.brightcove.com/v4/access_token"
+    private val backend = HttpClientSyncBackend() // Or AsyncHttpClientFutureBackend()
+
+    def getToken(clientID: String, clientSecret: String): Either[String, String] = {
+      val request =
+        basicRequest.auth
+          .basic(clientID, clientSecret)
+          .post(uri"$authUrl?grant_type=client_credentials")
+      val authResponse = request.send(backend)
+
+      authResponse.body match {
+        case Right(jsonString) =>
+          decode[TokenResponse](jsonString) match {
+            case Right(tokenResponse) => Right(tokenResponse.access_token)
+            case Left(error)          => Left(s"Failed to decode token response: ${error.getMessage}")
+          }
+        case Left(error) => Left(s"Failed to get token: ${error}")
+      }
+    }
+
+    def getVideoSource(accountId: String, videoId: String, bearerToken: String): Either[String, Vector[Json]] = {
+
+      val videoSourceUrl = uri"https://cms.api.brightcove.com/v1/accounts/$accountId/videos/$videoId/sources"
+      val request = basicRequest
+        .header("Authorization", s"Bearer $bearerToken")
+        .get(videoSourceUrl)
+
+      implicit val backend = HttpClientSyncBackend()
+
+      val response = request.send(backend)
+
+      response.body match {
+        case Right(jsonString) =>
+          parse(jsonString) match {
+            case Right(json) =>
+              json.asArray match {
+                case Some(videoSources) => Right(videoSources)
+                case None               => Left("Expected a JSON array but got something else.")
+              }
+            case Left(error) => Left(s"Failed to decode video source response: ${error.getMessage}")
+          }
+        case Left(error) => Left(s"Failed to get video source: ${error}")
+      }
+    }
+  }
+}
diff --git a/project/Dependencies.scala b/project/Dependencies.scala
index 99c72f0c3..42fee02c0 100644
--- a/project/Dependencies.scala
+++ b/project/Dependencies.scala
@@ -134,5 +134,9 @@ object Dependencies {
       "org.apache.httpcomponents" % "httpclient"    % "4.5.14",
       "org.yaml"                  % "snakeyaml"     % "2.0"
     )
+    lazy val jave: Seq[ModuleID] = Seq(
+      "ws.schild" % "jave-core"     % "3.5.0",
+      "ws.schild" % "jave-all-deps" % "3.5.0"
+    )
   }
 }
diff --git a/project/Module.scala b/project/Module.scala
index ed4fd485d..2ec80029a 100644
--- a/project/Module.scala
+++ b/project/Module.scala
@@ -168,7 +168,6 @@ trait Module {
       )
     )
   }
-
   val checkfmt = taskKey[Unit]("Check for code style errors")
   val fmt      = taskKey[Unit]("Automatically apply code style fixes")
 
diff --git a/project/audioapi.scala b/project/audioapi.scala
index 716f544e7..7ca36a8b3 100644
--- a/project/audioapi.scala
+++ b/project/audioapi.scala
@@ -23,7 +23,8 @@ object audioapi extends Module {
     elastic4s,
     database,
     tapirHttp4sCirce,
-    vulnerabilityOverrides
+    vulnerabilityOverrides,
+    jave
   )
 
   lazy val tsSettings: Seq[Def.Setting[?]] = typescriptSettings(

From f46fd636188db4a8d864338792351a560f7646e0 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Fri, 6 Dec 2024 12:56:21 +0100
Subject: [PATCH 02/31] Add get endpoint

---
 .../no/ndla/audioapi/AudioApiProperties.scala |  4 +--
 .../no/ndla/audioapi/ComponentRegistry.scala  |  5 +--
 .../controller/TranscriptionController.scala  | 35 ++++++++++++++-----
 .../service/TranscriptionService.scala        | 15 +++++---
 .../brightcove/NdlaBrightcoveClient.scala     | 18 +---------
 5 files changed, 44 insertions(+), 33 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala b/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
index 2b6cdf5d5..3430227d1 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
@@ -37,12 +37,12 @@ class AudioApiProperties extends BaseProps with DatabaseProps with StrictLogging
   val StorageName: String           = propOrElse("AUDIO_FILE_S3_BUCKET", s"$Environment.audio.ndla")
   val StorageRegion: Option[String] = propOrNone("AUDIO_FILE_S3_BUCKET_REGION")
 
-  val TranscribeStorageName: String           = propOrElse("TRANSCRIBE_FILE_S3_BUCKET", s"$Environment.transcribe.ndla")
+  val TranscribeStorageName: String = propOrElse("TRANSCRIBE_FILE_S3_BUCKET_NAME", s"$Environment.transcribe.ndla")
   val TranscribeStorageRegion: Option[String] = propOrNone("TRANSCRIBE_FILE_S3_BUCKET_REGION")
 
   val BrightcoveClientId: String     = prop("BRIGHTCOVE_API_CLIENT_ID")
   val BrightcoveClientSecret: String = prop("BRIGHTCOVE_API_CLIENT_SECRET")
-  val BrightcoveAccountId: String    = prop("BRIGHTCOVE_ACCOUNT")
+  val BrightcoveAccountId: String    = prop("NDLA_BRIGHTCOVE_ACCOUNT_ID")
 
   val SearchServer: String                 = propOrElse("SEARCH_SERVER", "http://search-audio-api.ndla-local")
   val RunWithSignedSearchRequests: Boolean = propOrElse("RUN_WITH_SIGNED_SEARCH_REQUESTS", "true").toBoolean
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala b/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala
index 56f2049cf..906104bb7 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala
@@ -67,8 +67,9 @@ class ComponentRegistry(properties: AudioApiProperties)
   override val dataSource: HikariDataSource = DataSource.getHikariDataSource
   DataSource.connectToDatabase()
 
-  lazy val s3Client         = new NdlaS3Client(props.StorageName, props.StorageRegion)
-  lazy val brightcoveClient = new NdlaBrightcoveClient()
+  lazy val s3Client           = new NdlaS3Client(props.StorageName, props.StorageRegion)
+  lazy val s3TranscribeClient = new NdlaS3Client(props.TranscribeStorageName, props.TranscribeStorageRegion)
+  lazy val brightcoveClient   = new NdlaBrightcoveClient()
 
   lazy val audioRepository  = new AudioRepository
   lazy val seriesRepository = new SeriesRepository
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index 1b77682c2..55519e6f5 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -4,8 +4,9 @@ import no.ndla.audioapi.Props
 import no.ndla.audioapi.service.{ReadService, TranscriptionService}
 import no.ndla.network.tapir.TapirController
 import no.ndla.network.tapir.TapirUtil.errorOutputsFor
+import no.ndla.network.tapir.auth.Permission.DRAFT_API_WRITE
 import sttp.tapir.server.ServerEndpoint
-import sttp.tapir.{EndpointInput, endpoint, path, query}
+import sttp.tapir.{EndpointInput, endpoint, path}
 import sttp.tapir.*
 
 import scala.util.{Failure, Success}
@@ -13,13 +14,12 @@ trait TranscriptionController {
   this: Props & TapirController & ReadService & TranscriptionService =>
   val transcriptionController: TranscriptionController
   class TranscriptionController() extends TapirController {
-    import props.*
 
     override val serviceName: String         = "transcription"
     override val prefix: EndpointInput[Unit] = "audio-api" / "v1" / serviceName
 
     private val videoId  = path[String]("videoId").description("The video id to transcribe")
-    private val language = query[String]("language").description("The language to transcribe the video to")
+    private val language = path[String]("language").description("The language to transcribe the video to")
 
     def postExtractAudio: ServerEndpoint[Any, Eff] = endpoint.post
       .summary("Extract audio from video")
@@ -27,14 +27,33 @@ trait TranscriptionController {
       .in(videoId)
       .in(language)
       .errorOut(errorOutputsFor(400, 500))
-      .serverLogicPure { case (videoId, language) =>
-        transcriptionService.extractAudioFromVideo(videoId, language) match {
-          case Success(_)  => Right(())
-          case Failure(ex) => returnLeftError(ex)
+      .requirePermission(DRAFT_API_WRITE)
+      .serverLogicPure { _ =>
+        { case (videoId, language) =>
+          transcriptionService.extractAudioFromVideo(videoId, language) match {
+            case Success(_)  => Right(())
+            case Failure(ex) => returnLeftError(ex)
+          }
         }
       }
 
-    override val endpoints: List[ServerEndpoint[Any, Eff]] = List(postExtractAudio)
+    def getAudioExtraction: ServerEndpoint[Any, Eff] = endpoint.get
+      .summary("Get audio extraction status")
+      .description("Get the status of the audio extraction from a Brightcove video.")
+      .in(videoId)
+      .in(language)
+      .errorOut(errorOutputsFor(400, 500))
+      .requirePermission(DRAFT_API_WRITE)
+      .serverLogicPure { _ =>
+        { case (videoId, language) =>
+          transcriptionService.getAudioExtractionStatus(videoId, language) match {
+            case Success(_)  => Right(())
+            case Failure(ex) => returnLeftError(ex)
+          }
+        }
+      }
+
+    override val endpoints: List[ServerEndpoint[Any, Eff]] = List(postExtractAudio, getAudioExtraction)
   }
 
 }
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index a0e1b1274..53e9af0e6 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -13,9 +13,9 @@ import scala.util.{Failure, Success, Try}
 trait TranscriptionService {
   this: NdlaS3Client & Props & NdlaBrightcoveClient =>
   val transcriptionService: TranscriptionService
-  class TranscriptionService {
+  val s3TranscribeClient: NdlaS3Client
 
-    private lazy val s3TranscribeClient = new NdlaS3Client(props.TranscribeStorageName, props.TranscribeStorageRegion)
+  class TranscriptionService {
 
     def extractAudioFromVideo(videoId: String, language: String): Try[Unit] = {
       val accountId = props.BrightcoveAccountId
@@ -46,14 +46,21 @@ trait TranscriptionService {
           s3TranscribeClient.putObject(s3Key, audioFile, "audio/mpeg") match {
             case Success(_) =>
               s3TranscribeClient.deleteObject(videoFile.getName).map(_ => ())
-            case _ =>
-              Failure(new RuntimeException(s"Failed to upload audio file to S3."))
+            case Failure(ex) =>
+              Failure(new RuntimeException(s"Failed to upload audio file to S3.", ex))
           }
         case Failure(exception) => Failure(exception)
 
       }
     }
 
+    def getAudioExtractionStatus(videoId: String, language: String): Try[Unit] = {
+      s3TranscribeClient.getObject(s"audio/$language/${videoId}.mp3") match {
+        case Success(_)         => Success(())
+        case Failure(exception) => Failure(exception)
+      }
+    }
+
     private def getVideo(accountId: String, videoId: String): Either[String, Vector[String]] = {
       val clientId     = props.BrightcoveClientId
       val clientSecret = props.BrightcoveClientSecret
diff --git a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
index 25b646304..135c7f399 100644
--- a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
+++ b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
@@ -1,27 +1,11 @@
 package no.ndla.common.brightcove
 
-import io.circe.{Decoder, Json}
+import io.circe.Json
 import io.circe.generic.codec.DerivedAsObjectCodec.deriveCodec
-import io.circe.generic.semiauto.deriveDecoder
 import io.circe.parser.*
 import sttp.client3.{HttpClientSyncBackend, UriContext, basicRequest}
 
 case class TokenResponse(access_token: String, token_type: String, expires_in: Int)
-case class VideoSource(
-    src: String,
-    `type`: String,
-    container: String,
-    codec: Option[String] = None,
-    encoding_rate: Option[Int] = None,
-    duration: Option[Int] = None,
-    height: Option[Int] = None,
-    width: Option[Int] = None,
-    size: Option[Long] = None,
-    uploaded_at: Option[String] = None,
-    ext_x_version: Option[String] = None,
-    profiles: Option[String] = None,
-    remote: Option[Boolean] = None
-)
 
 trait NdlaBrightcoveClient {
   val brightcoveClient: NdlaBrightcoveClient

From 873028897b1a1abb4468d3416ce5447f44a66820 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Thu, 12 Dec 2024 09:13:31 +0100
Subject: [PATCH 03/31] Update NotFound Error handling in audio-api

---
 .../scala/no/ndla/audioapi/model/api/Error.scala  | 15 +++++++--------
 .../no/ndla/audioapi/service/ReadService.scala    |  5 ++---
 .../no/ndla/audioapi/service/WriteService.scala   |  6 +++---
 .../ndla/audioapi/service/WriteServiceTest.scala  |  4 ++--
 .../ndla/common/aws/NdlaAWSTranscribeClient.scala |  3 +++
 5 files changed, 17 insertions(+), 16 deletions(-)
 create mode 100644 common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/model/api/Error.scala b/audio-api/src/main/scala/no/ndla/audioapi/model/api/Error.scala
index bfc3d8c7c..f2b294366 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/model/api/Error.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/model/api/Error.scala
@@ -10,7 +10,7 @@ package no.ndla.audioapi.model.api
 
 import no.ndla.audioapi.Props
 import no.ndla.common.Clock
-import no.ndla.common.errors.{AccessDeniedException, FileTooBigException, ValidationException}
+import no.ndla.common.errors.{AccessDeniedException, FileTooBigException, NotFoundException, ValidationException}
 import no.ndla.database.DataSource
 import no.ndla.network.model.HttpRequestException
 import no.ndla.network.tapir.{AllErrors, ErrorBody, TapirErrorHandling, ValidationErrorBody}
@@ -59,10 +59,9 @@ trait ErrorHandling extends TapirErrorHandling {
 
 }
 
-class NotFoundException(message: String = "The audio was not found") extends RuntimeException(message)
-case class MissingIdException(message: String)                       extends RuntimeException(message)
-case class CouldNotFindLanguageException(message: String)            extends RuntimeException(message)
-class AudioStorageException(message: String)                         extends RuntimeException(message)
-class LanguageMappingException(message: String)                      extends RuntimeException(message)
-class ImportException(message: String)                               extends RuntimeException(message)
-case class ElasticIndexingException(message: String)                 extends RuntimeException(message)
+case class MissingIdException(message: String)            extends RuntimeException(message)
+case class CouldNotFindLanguageException(message: String) extends RuntimeException(message)
+class AudioStorageException(message: String)              extends RuntimeException(message)
+class LanguageMappingException(message: String)           extends RuntimeException(message)
+class ImportException(message: String)                    extends RuntimeException(message)
+case class ElasticIndexingException(message: String)      extends RuntimeException(message)
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/ReadService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/ReadService.scala
index d9682baf9..fd954c354 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/ReadService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/ReadService.scala
@@ -8,12 +8,11 @@
 
 package no.ndla.audioapi.service
 
-import cats.implicits._
+import cats.implicits.*
 import no.ndla.audioapi.model.api
-import no.ndla.audioapi.model.api.NotFoundException
 import no.ndla.audioapi.repository.{AudioRepository, SeriesRepository}
 import no.ndla.audioapi.service.search.{SearchConverterService, TagSearchService}
-import no.ndla.common.errors.ValidationException
+import no.ndla.common.errors.{NotFoundException, ValidationException}
 
 import scala.util.{Failure, Success, Try}
 
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/WriteService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/WriteService.scala
index 47a0a6c23..a94213c07 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/WriteService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/WriteService.scala
@@ -9,14 +9,14 @@ package no.ndla.audioapi.service
 
 import cats.implicits.*
 import com.typesafe.scalalogging.StrictLogging
-import no.ndla.audioapi.model.api.{AudioStorageException, MissingIdException, NotFoundException}
+import no.ndla.audioapi.model.api.{AudioStorageException, MissingIdException}
 import no.ndla.audioapi.model.domain.Audio
 import no.ndla.audioapi.model.{api, domain}
 import no.ndla.audioapi.repository.{AudioRepository, SeriesRepository}
 import no.ndla.audioapi.service.search.{AudioIndexService, SeriesIndexService, TagIndexService}
 import no.ndla.common.Clock
 import no.ndla.common.aws.NdlaS3Client
-import no.ndla.common.errors.ValidationException
+import no.ndla.common.errors.{NotFoundException, ValidationException}
 import no.ndla.common.model.domain.UploadedFile
 import no.ndla.common.model.domain as common
 import no.ndla.language.Language.findByLanguageOrBestEffort
@@ -278,7 +278,7 @@ trait WriteService {
         user: TokenUser
     ): Try[api.AudioMetaInformation] = {
       audioRepository.withId(id) match {
-        case None => Failure(new NotFoundException)
+        case None => Failure(NotFoundException("Audio not found"))
         case Some(existingMetadata) =>
           val metadataAndFile = fileOpt match {
             case None => mergeAudioMeta(existingMetadata, metadataToUpdate, None, user)
diff --git a/audio-api/src/test/scala/no/ndla/audioapi/service/WriteServiceTest.scala b/audio-api/src/test/scala/no/ndla/audioapi/service/WriteServiceTest.scala
index dba17278f..1f15dba0b 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/service/WriteServiceTest.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/service/WriteServiceTest.scala
@@ -12,7 +12,7 @@ import no.ndla.audioapi.model.api.*
 import no.ndla.audioapi.model.domain.{Audio, AudioType}
 import no.ndla.audioapi.model.{api, domain}
 import no.ndla.audioapi.{TestData, TestEnvironment, UnitSuite}
-import no.ndla.common.errors.{ValidationException, ValidationMessage}
+import no.ndla.common.errors.{NotFoundException, ValidationException, ValidationMessage}
 import no.ndla.common.model
 import no.ndla.common.model.api.{Copyright, License}
 import no.ndla.common.model.domain.UploadedFile
@@ -393,7 +393,7 @@ class WriteServiceTest extends UnitSuite with TestEnvironment {
 
     val result = writeService.updateAudio(1, updatedAudioMeta, None, testUser)
     result.isFailure should be(true)
-    result.failed.get.getMessage should equal(new NotFoundException().getMessage)
+    result.failed.get.getMessage should equal(NotFoundException("Audio not found").getMessage)
   }
 
   test("that updateAudio returns Failure when audio file validation fails") {
diff --git a/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala b/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
new file mode 100644
index 000000000..a17bc22a3
--- /dev/null
+++ b/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
@@ -0,0 +1,3 @@
+package no.ndla.common.aws trait NdlaAWSTranscribeClient {
+
+}

From 37edf26a0d7073e11595c87080deb100acf29e2c Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Thu, 12 Dec 2024 09:16:19 +0100
Subject: [PATCH 04/31] Add transcription client

---
 .../no/ndla/audioapi/ComponentRegistry.scala  |  4 +-
 .../controller/InternController.scala         |  5 +-
 .../no/ndla/audioapi/TestEnvironment.scala    | 20 +++--
 .../common/aws/NdlaAWSTranscribeClient.scala  | 75 ++++++++++++++++++-
 project/Dependencies.scala                    |  4 +
 project/commonlib.scala                       |  1 +
 6 files changed, 99 insertions(+), 10 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala b/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala
index 906104bb7..4d055dd79 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/ComponentRegistry.scala
@@ -16,7 +16,7 @@ import no.ndla.audioapi.repository.{AudioRepository, SeriesRepository}
 import no.ndla.audioapi.service.*
 import no.ndla.audioapi.service.search.*
 import no.ndla.common.Clock
-import no.ndla.common.aws.NdlaS3Client
+import no.ndla.common.aws.{NdlaAWSTranscribeClient, NdlaS3Client}
 import no.ndla.common.brightcove.NdlaBrightcoveClient
 import no.ndla.common.configuration.BaseComponentRegistry
 import no.ndla.database.{DBMigrator, DataSource}
@@ -58,6 +58,7 @@ class ComponentRegistry(properties: AudioApiProperties)
     with SwaggerDocControllerConfig
     with NdlaS3Client
     with TranscriptionService
+    with NdlaAWSTranscribeClient
     with NdlaBrightcoveClient {
   override val props: AudioApiProperties = properties
   override val migrator: DBMigrator = DBMigrator(
@@ -70,6 +71,7 @@ class ComponentRegistry(properties: AudioApiProperties)
   lazy val s3Client           = new NdlaS3Client(props.StorageName, props.StorageRegion)
   lazy val s3TranscribeClient = new NdlaS3Client(props.TranscribeStorageName, props.TranscribeStorageRegion)
   lazy val brightcoveClient   = new NdlaBrightcoveClient()
+  lazy val transcribeClient   = new NdlaAWSTranscribeClient(props.TranscribeStorageRegion)
 
   lazy val audioRepository  = new AudioRepository
   lazy val seriesRepository = new SeriesRepository
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/InternController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/InternController.scala
index 6e02d4803..0848543b4 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/InternController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/InternController.scala
@@ -12,11 +12,12 @@ import cats.implicits.*
 import io.circe.generic.auto.*
 import no.ndla.audioapi.Props
 import no.ndla.audioapi.model.api
-import no.ndla.audioapi.model.api.{AudioMetaDomainDump, ErrorHandling, NotFoundException}
+import no.ndla.audioapi.model.api.{AudioMetaDomainDump, ErrorHandling}
 import no.ndla.audioapi.model.domain.AudioMetaInformation
 import no.ndla.audioapi.repository.AudioRepository
 import no.ndla.audioapi.service.search.{AudioIndexService, SeriesIndexService, TagIndexService}
 import no.ndla.audioapi.service.{ConverterService, ReadService}
+import no.ndla.common.errors.NotFoundException
 import no.ndla.network.tapir.NoNullJsonPrinter.jsonBody
 import no.ndla.network.tapir.TapirController
 import no.ndla.network.tapir.TapirUtil.errorOutputsFor
@@ -116,7 +117,7 @@ trait InternController {
         .serverLogicPure { id =>
           audioRepository.withId(id) match {
             case Some(image) => image.asRight
-            case None        => returnLeftError(new NotFoundException(s"Could not find audio with id: '$id'"))
+            case None        => returnLeftError(NotFoundException(s"Could not find audio with id: '$id'"))
           }
         },
       endpoint.post
diff --git a/audio-api/src/test/scala/no/ndla/audioapi/TestEnvironment.scala b/audio-api/src/test/scala/no/ndla/audioapi/TestEnvironment.scala
index 5f006c814..101529331 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/TestEnvironment.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/TestEnvironment.scala
@@ -15,7 +15,8 @@ import no.ndla.audioapi.repository.{AudioRepository, SeriesRepository}
 import no.ndla.audioapi.service.*
 import no.ndla.audioapi.service.search.*
 import no.ndla.common.Clock
-import no.ndla.common.aws.NdlaS3Client
+import no.ndla.common.aws.{NdlaAWSTranscribeClient, NdlaS3Client}
+import no.ndla.common.brightcove.NdlaBrightcoveClient
 import no.ndla.database.DataSource
 import no.ndla.network.NdlaClient
 import no.ndla.network.tapir.TapirApplication
@@ -51,6 +52,9 @@ trait TestEnvironment
     with MockitoSugar
     with Clock
     with Props
+    with TranscriptionService
+    with NdlaAWSTranscribeClient
+    with NdlaBrightcoveClient
     with ErrorHandling {
   override val props: AudioApiProperties = new AudioApiProperties
 
@@ -59,15 +63,19 @@ trait TestEnvironment
   val audioRepository: AudioRepository   = mock[AudioRepository]
   val seriesRepository: SeriesRepository = mock[SeriesRepository]
 
-  val s3Client: NdlaS3Client = mock[NdlaS3Client]
+  val s3Client: NdlaS3Client                    = mock[NdlaS3Client]
+  val brightcoveClient: NdlaBrightcoveClient    = mock[NdlaBrightcoveClient]
+  val transcribeClient: NdlaAWSTranscribeClient = mock[NdlaAWSTranscribeClient]
 
   val ndlaClient: NdlaClient           = mock[NdlaClient]
   val myndlaApiClient: MyNDLAApiClient = mock[MyNDLAApiClient]
 
-  val readService: ReadService             = mock[ReadService]
-  val writeService: WriteService           = mock[WriteService]
-  val validationService: ValidationService = mock[ValidationService]
-  val converterService: ConverterService   = mock[ConverterService]
+  val readService: ReadService                   = mock[ReadService]
+  val writeService: WriteService                 = mock[WriteService]
+  val validationService: ValidationService       = mock[ValidationService]
+  val converterService: ConverterService         = mock[ConverterService]
+  val transcriptionService: TranscriptionService = mock[TranscriptionService]
+  val s3TranscribeClient: NdlaS3Client           = mock[NdlaS3Client]
 
   val internController: InternController  = mock[InternController]
   val audioApiController: AudioController = mock[AudioController]
diff --git a/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala b/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
index a17bc22a3..4689207f6 100644
--- a/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
+++ b/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
@@ -1,3 +1,76 @@
-package no.ndla.common.aws trait NdlaAWSTranscribeClient {
+/*
+ * Part of NDLA common
+ * Copyright (C) 2024 NDLA
+ *
+ * See LICENSE
+ */
 
+package no.ndla.common.aws
+
+import software.amazon.awssdk.services.transcribe.{TranscribeClient, TranscribeClientBuilder}
+import software.amazon.awssdk.services.transcribe.model.*
+
+import scala.util.{Failure, Try}
+
+trait NdlaAWSTranscribeClient {
+  val transcribeClient: NdlaAWSTranscribeClient
+
+  class NdlaAWSTranscribeClient(region: Option[String]) {
+
+    private val builder: TranscribeClientBuilder = TranscribeClient.builder()
+
+    val client: TranscribeClient = region match {
+      case Some(value) => builder.region(software.amazon.awssdk.regions.Region.of(value)).build()
+      case None        => builder.build()
+    }
+
+    def startTranscriptionJob(
+        jobName: String,
+        mediaUri: String,
+        mediaFormat: String,
+        languageCode: String
+    ): Try[StartTranscriptionJobResponse] = Try {
+      val request = StartTranscriptionJobRequest
+        .builder()
+        .transcriptionJobName(jobName)
+        .media(Media.builder().mediaFileUri(mediaUri).build())
+        .mediaFormat(mediaFormat)
+        .languageCode(languageCode)
+        .build()
+
+      client.startTranscriptionJob(request)
+    }
+
+    def getTranscriptionJob(jobName: String): Try[GetTranscriptionJobResponse] = {
+      Try {
+        val request = GetTranscriptionJobRequest
+          .builder()
+          .transcriptionJobName(jobName)
+          .build()
+        client.getTranscriptionJob(request)
+      }.recoverWith { case e: BadRequestException =>
+        val nfe = no.ndla.common.errors.NotFoundException("Transcription job not found")
+        Failure(nfe.initCause(e))
+      }
+    }
+
+    def listTranscriptionJobs(status: Option[String] = None): Try[ListTranscriptionJobsResponse] = Try {
+      val requestBuilder = ListTranscriptionJobsRequest.builder()
+      val request = status match {
+        case Some(jobStatus) => requestBuilder.status(jobStatus).build()
+        case None            => requestBuilder.build()
+      }
+
+      client.listTranscriptionJobs(request)
+    }
+
+    def deleteTranscriptionJob(jobName: String): Try[DeleteTranscriptionJobResponse] = Try {
+      val request = DeleteTranscriptionJobRequest
+        .builder()
+        .transcriptionJobName(jobName)
+        .build()
+
+      client.deleteTranscriptionJob(request)
+    }
+  }
 }
diff --git a/project/Dependencies.scala b/project/Dependencies.scala
index 42fee02c0..b15962d1d 100644
--- a/project/Dependencies.scala
+++ b/project/Dependencies.scala
@@ -65,6 +65,10 @@ object Dependencies {
       "software.amazon.awssdk" % "s3" % AwsSdkV
     )
 
+    lazy val awsTranscribe: Seq[ModuleID] = Seq(
+      "software.amazon.awssdk" % "transcribe" % AwsSdkV
+    )
+
     lazy val awsCloudwatch: Seq[ModuleID] = Seq(
       "software.amazon.awssdk" % "cloudwatch" % AwsSdkV
     )
diff --git a/project/commonlib.scala b/project/commonlib.scala
index 0e8dfabff..40582a16c 100644
--- a/project/commonlib.scala
+++ b/project/commonlib.scala
@@ -17,6 +17,7 @@ object commonlib extends Module {
       scalaTsi
     ),
     awsS3,
+    awsTranscribe,
     melody,
     tapirHttp4sCirce
   )

From 87f3560a8c92189bd66693201dc852e5193a8281 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Thu, 12 Dec 2024 09:18:36 +0100
Subject: [PATCH 05/31] Add Transcription endpoints

---
 .../controller/TranscriptionController.scala  | 54 +++++++++++++++++-
 .../service/TranscriptionService.scala        | 56 +++++++++++++++++--
 .../service/TranscriptionServiceTest.scala    | 27 ++++++++-
 3 files changed, 130 insertions(+), 7 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index 55519e6f5..fefbbaa9e 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -26,6 +26,7 @@ trait TranscriptionController {
       .description("Extracts audio from a Brightcove video and uploads it to S3.")
       .in(videoId)
       .in(language)
+      .in("extract-audio")
       .errorOut(errorOutputsFor(400, 500))
       .requirePermission(DRAFT_API_WRITE)
       .serverLogicPure { _ =>
@@ -42,6 +43,7 @@ trait TranscriptionController {
       .description("Get the status of the audio extraction from a Brightcove video.")
       .in(videoId)
       .in(language)
+      .in("extract-audio")
       .errorOut(errorOutputsFor(400, 500))
       .requirePermission(DRAFT_API_WRITE)
       .serverLogicPure { _ =>
@@ -53,7 +55,57 @@ trait TranscriptionController {
         }
       }
 
-    override val endpoints: List[ServerEndpoint[Any, Eff]] = List(postExtractAudio, getAudioExtraction)
+    def postTranscription: ServerEndpoint[Any, Eff] = endpoint.post
+      .summary("Transcribe video")
+      .description("Transcribes a video to a specific language, and uploads the transcription to S3.")
+      .in(videoId)
+      .in(language)
+      .errorOut(errorOutputsFor(400, 500))
+      .requirePermission(DRAFT_API_WRITE)
+      .serverLogicPure { _ =>
+        { case (videoId, language) =>
+          transcriptionService.transcribeVideo(videoId, language) match {
+            case Success(_)  => Right(())
+            case Failure(ex) => returnLeftError(ex)
+          }
+        }
+      }
+
+    def getTranscription: ServerEndpoint[Any, Eff] = endpoint.get
+      .summary("Get transcription")
+      .description("Get the transcription of a video.")
+      .in(videoId)
+      .in(language)
+      .errorOut(errorOutputsFor(400, 404, 500))
+      .requirePermission(DRAFT_API_WRITE)
+      .serverLogicPure { _ =>
+        { case (videoId, language) =>
+          transcriptionService.getTranscription(videoId, language) match {
+            case Success(_)                          => Right(())
+            case Failure(ex: NoSuchElementException) => returnLeftError(ex)
+            case Failure(ex)                         => returnLeftError(ex)
+          }
+        }
+      }
+
+    /*def postTranscriptionFormatting: ServerEndpoint[Any, Eff] = endpoint.post
+      .summary("Format transcription")
+      .description("Formats a transcription to a specific format.")
+      .in(videoId)
+      .in(language)
+      .errorOut(errorOutputsFor(400, 500))
+      .requirePermission(DRAFT_API_WRITE)
+      .serverLogicPure { _ =>
+        { case (videoId, language) =>
+          transcriptionService.formatTranscription(videoId, language) match {
+            case Success(_)  => Right(())
+            case Failure(ex) => returnLeftError(ex)
+          }
+        }
+      }*/
+
+    override val endpoints: List[ServerEndpoint[Any, Eff]] =
+      List(postExtractAudio, getAudioExtraction, postTranscription, getTranscription)
   }
 
 }
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index 53e9af0e6..90dfb1173 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -1,7 +1,8 @@
 package no.ndla.audioapi.service
 
+import com.typesafe.scalalogging.StrictLogging
 import no.ndla.audioapi.Props
-import no.ndla.common.aws.NdlaS3Client
+import no.ndla.common.aws.{NdlaAWSTranscribeClient, NdlaS3Client}
 import no.ndla.common.brightcove.NdlaBrightcoveClient
 import sttp.client3.{HttpURLConnectionBackend, UriContext, asFile, basicRequest}
 import ws.schild.jave.{Encoder, MultimediaObject}
@@ -11,11 +12,50 @@ import java.io.File
 import scala.util.{Failure, Success, Try}
 
 trait TranscriptionService {
-  this: NdlaS3Client & Props & NdlaBrightcoveClient =>
+  this: NdlaS3Client & Props & NdlaBrightcoveClient & NdlaAWSTranscribeClient =>
   val transcriptionService: TranscriptionService
   val s3TranscribeClient: NdlaS3Client
 
-  class TranscriptionService {
+  class TranscriptionService extends StrictLogging {
+
+    def transcribeVideo(videoId: String, language: String): Try[Unit] = {
+      getAudioExtractionStatus(videoId, language) match {
+        case Success(_) =>
+          logger.info(s"Audio already extracted for videoId: $videoId")
+        case Failure(_) =>
+          logger.info(s"Audio extraction required for videoId: $videoId")
+          extractAudioFromVideo(videoId, language) match {
+            case Success(_) =>
+              logger.info(s"Audio extracted for videoId: $videoId")
+            case Failure(exception) =>
+              return Failure(new RuntimeException(s"Failed to extract audio for videoId: $videoId", exception))
+
+          }
+      }
+
+      val audioUri = s"s3://${props.TranscribeStorageName}/audio/$language/$videoId.mp3"
+      logger.info(s"Transcribing audio from: $audioUri")
+      val jobName      = s"transcription-$videoId-$language"
+      val mediaFormat  = "mp3"
+      val languageCode = language
+
+      transcribeClient.startTranscriptionJob(jobName, audioUri, mediaFormat, languageCode) match {
+        case Success(_) =>
+          logger.info(s"Transcription job started for videoId: $videoId")
+          Success(())
+        case Failure(exception) =>
+          Failure(new RuntimeException(s"Failed to start transcription for videoId: $videoId", exception))
+      }
+    }
+
+    def getTranscription(videoId: String, language: String): Try[String] = {
+      val jobName = s"transcription-$videoId-$language"
+
+      transcribeClient.getTranscriptionJob(jobName).map { transcriptionJobResponse =>
+        val transcriptionJobStatus = transcriptionJobResponse.transcriptionJob().transcriptionJobStatus()
+        transcriptionJobStatus.toString
+      }
+    }
 
     def extractAudioFromVideo(videoId: String, language: String): Try[Unit] = {
       val accountId = props.BrightcoveAccountId
@@ -42,10 +82,16 @@ trait TranscriptionService {
         encoder.encode(new MultimediaObject(videoFile), audioFile, encodingAttributes)
       } match {
         case Success(_) =>
-          val s3Key = s"/audio/$language/${videoId}.mp3"
+          logger.info("dasjhkdaidashjdas")
+          val s3Key = s"audio/$language/$videoId.mp3"
+          logger.info(s"Uploading audio file to S3: $s3Key")
           s3TranscribeClient.putObject(s3Key, audioFile, "audio/mpeg") match {
             case Success(_) =>
-              s3TranscribeClient.deleteObject(videoFile.getName).map(_ => ())
+              logger.info(s"Audio file uploaded to S3: $s3Key")
+              for {
+                _ <- Try(audioFile.delete())
+                _ <- Try(videoFile.delete())
+              } yield ()
             case Failure(ex) =>
               Failure(new RuntimeException(s"Failed to upload audio file to S3.", ex))
           }
diff --git a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
index c15bf9f21..5d8673f25 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
@@ -1,3 +1,28 @@
-package no.ndla.audioapi.service class TranscriptionServiceTest {
+package no.ndla.audioapi.service
 
+import no.ndla.audioapi.{AudioApiProperties, TestEnvironment, UnitSuite}
+import no.ndla.common.aws.NdlaS3Object
+import org.mockito.ArgumentMatchers.any
+import org.mockito.Mockito.when
+
+import scala.util.{Failure, Success, Try}
+
+class TranscriptionServiceTest extends UnitSuite with TestEnvironment {
+  override val transcriptionService: TranscriptionService = new TranscriptionService
+  override val brightcoveClient: NdlaBrightcoveClient     = new NdlaBrightcoveClient
+  override val props: AudioApiProperties = new AudioApiProperties {
+    override val BrightcoveAccountId: String    = "123"
+    override val BrightcoveClientId: String     = "123"
+    override val BrightcoveClientSecret: String = "123"
+  }
+
+  test("getAudioExtractionStatus returns Success when audio file exists") {
+    val videoId      = "1"
+    val language     = "en"
+    val fakeS3Object = mock[NdlaS3Object]
+    when(s3TranscribeClient.getObject(any)).thenReturn(Success(fakeS3Object))
+    val result = transcriptionService.getAudioExtractionStatus(videoId, language)
+
+    result should be(Success(()))
+  }
 }

From 68690a5e6f76f5120ba41bb6972b49004737a0e4 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Thu, 12 Dec 2024 12:28:49 +0100
Subject: [PATCH 06/31] Add maxSpeakers and subtitles

---
 .../controller/TranscriptionController.scala  | 23 ++++---------------
 .../service/TranscriptionService.scala        | 13 +++++++++--
 .../common/aws/NdlaAWSTranscribeClient.scala  | 23 +++++++++++++++++--
 3 files changed, 37 insertions(+), 22 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index fefbbaa9e..ea2344344 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -20,6 +20,8 @@ trait TranscriptionController {
 
     private val videoId  = path[String]("videoId").description("The video id to transcribe")
     private val language = path[String]("language").description("The language to transcribe the video to")
+    private val maxSpeaker =
+      query[Int]("maxSpeaker").description("The maximum number of speakers in the video").default(2)
 
     def postExtractAudio: ServerEndpoint[Any, Eff] = endpoint.post
       .summary("Extract audio from video")
@@ -60,11 +62,12 @@ trait TranscriptionController {
       .description("Transcribes a video to a specific language, and uploads the transcription to S3.")
       .in(videoId)
       .in(language)
+      .in(maxSpeaker)
       .errorOut(errorOutputsFor(400, 500))
       .requirePermission(DRAFT_API_WRITE)
       .serverLogicPure { _ =>
-        { case (videoId, language) =>
-          transcriptionService.transcribeVideo(videoId, language) match {
+        { case (videoId, language, maxSpeakerOpt) =>
+          transcriptionService.transcribeVideo(videoId, language, maxSpeakerOpt) match {
             case Success(_)  => Right(())
             case Failure(ex) => returnLeftError(ex)
           }
@@ -88,22 +91,6 @@ trait TranscriptionController {
         }
       }
 
-    /*def postTranscriptionFormatting: ServerEndpoint[Any, Eff] = endpoint.post
-      .summary("Format transcription")
-      .description("Formats a transcription to a specific format.")
-      .in(videoId)
-      .in(language)
-      .errorOut(errorOutputsFor(400, 500))
-      .requirePermission(DRAFT_API_WRITE)
-      .serverLogicPure { _ =>
-        { case (videoId, language) =>
-          transcriptionService.formatTranscription(videoId, language) match {
-            case Success(_)  => Right(())
-            case Failure(ex) => returnLeftError(ex)
-          }
-        }
-      }*/
-
     override val endpoints: List[ServerEndpoint[Any, Eff]] =
       List(postExtractAudio, getAudioExtraction, postTranscription, getTranscription)
   }
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index 90dfb1173..d197cc1c2 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -18,7 +18,7 @@ trait TranscriptionService {
 
   class TranscriptionService extends StrictLogging {
 
-    def transcribeVideo(videoId: String, language: String): Try[Unit] = {
+    def transcribeVideo(videoId: String, language: String, maxSpeakers: Int): Try[Unit] = {
       getAudioExtractionStatus(videoId, language) match {
         case Success(_) =>
           logger.info(s"Audio already extracted for videoId: $videoId")
@@ -37,9 +37,18 @@ trait TranscriptionService {
       logger.info(s"Transcribing audio from: $audioUri")
       val jobName      = s"transcription-$videoId-$language"
       val mediaFormat  = "mp3"
+      val outputKey    = s"transcription/$language/$videoId"
       val languageCode = language
 
-      transcribeClient.startTranscriptionJob(jobName, audioUri, mediaFormat, languageCode) match {
+      transcribeClient.startTranscriptionJob(
+        jobName,
+        audioUri,
+        mediaFormat,
+        languageCode,
+        props.TranscribeStorageName,
+        outputKey,
+        maxSpeakers
+      ) match {
         case Success(_) =>
           logger.info(s"Transcription job started for videoId: $videoId")
           Success(())
diff --git a/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala b/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
index 4689207f6..3ba02563f 100644
--- a/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
+++ b/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
@@ -7,8 +7,8 @@
 
 package no.ndla.common.aws
 
-import software.amazon.awssdk.services.transcribe.{TranscribeClient, TranscribeClientBuilder}
 import software.amazon.awssdk.services.transcribe.model.*
+import software.amazon.awssdk.services.transcribe.{TranscribeClient, TranscribeClientBuilder}
 
 import scala.util.{Failure, Try}
 
@@ -28,7 +28,11 @@ trait NdlaAWSTranscribeClient {
         jobName: String,
         mediaUri: String,
         mediaFormat: String,
-        languageCode: String
+        languageCode: String,
+        outputBucket: String,
+        outputKey: String,
+        maxSpeakers: Int,
+        outputSubtitleFormat: String = "VTT"
     ): Try[StartTranscriptionJobResponse] = Try {
       val request = StartTranscriptionJobRequest
         .builder()
@@ -36,6 +40,21 @@ trait NdlaAWSTranscribeClient {
         .media(Media.builder().mediaFileUri(mediaUri).build())
         .mediaFormat(mediaFormat)
         .languageCode(languageCode)
+        .outputBucketName(outputBucket)
+        .outputKey(outputKey)
+        .settings(
+          Settings
+            .builder()
+            .showSpeakerLabels(true)
+            .maxSpeakerLabels(maxSpeakers)
+            .build()
+        )
+        .subtitles(
+          Subtitles
+            .builder()
+            .formats(SubtitleFormat.valueOf(outputSubtitleFormat))
+            .build()
+        )
         .build()
 
       client.startTranscriptionJob(request)

From 117883855463b9387813c7ce898f67fb565564cb Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Thu, 12 Dec 2024 13:44:59 +0100
Subject: [PATCH 07/31] Fix test coverage for transcription service

---
 .../no/ndla/audioapi/TestEnvironment.scala    |  1 -
 .../scala/no/ndla/audioapi/UnitSuite.scala    |  3 ++
 .../service/TranscriptionServiceTest.scala    | 40 +++++++++++++++++++
 3 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/audio-api/src/test/scala/no/ndla/audioapi/TestEnvironment.scala b/audio-api/src/test/scala/no/ndla/audioapi/TestEnvironment.scala
index 101529331..a20e8992a 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/TestEnvironment.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/TestEnvironment.scala
@@ -59,7 +59,6 @@ trait TestEnvironment
   override val props: AudioApiProperties = new AudioApiProperties
 
   val dataSource: HikariDataSource       = mock[HikariDataSource]
-  val storageName: String                = props.StorageName
   val audioRepository: AudioRepository   = mock[AudioRepository]
   val seriesRepository: SeriesRepository = mock[SeriesRepository]
 
diff --git a/audio-api/src/test/scala/no/ndla/audioapi/UnitSuite.scala b/audio-api/src/test/scala/no/ndla/audioapi/UnitSuite.scala
index e06de1ad8..76d6f9edf 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/UnitSuite.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/UnitSuite.scala
@@ -24,4 +24,7 @@ trait UnitSuite extends UnitTestSuite with PrivateMethodTester {
   setPropEnv("SEARCH_REGION", "some-region")
   setPropEnv("RUN_WITH_SIGNED_SEARCH_REQUESTS", "false")
   setPropEnv("SEARCH_INDEX_NAME", "audio-integration-test-index")
+  setPropEnv("BRIGHTCOVE_API_CLIENT_ID", "client-id")
+  setPropEnv("BRIGHTCOVE_API_CLIENT_SECRET", "client")
+  setPropEnv("NDLA_BRIGHTCOVE_ACCOUNT_ID", "312532")
 }
diff --git a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
index 5d8673f25..2976f15c1 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
@@ -4,6 +4,12 @@ import no.ndla.audioapi.{AudioApiProperties, TestEnvironment, UnitSuite}
 import no.ndla.common.aws.NdlaS3Object
 import org.mockito.ArgumentMatchers.any
 import org.mockito.Mockito.when
+import software.amazon.awssdk.services.transcribe.model.{
+  GetTranscriptionJobResponse,
+  StartTranscriptionJobResponse,
+  TranscriptionJob,
+  TranscriptionJobStatus
+}
 
 import scala.util.{Failure, Success, Try}
 
@@ -25,4 +31,38 @@ class TranscriptionServiceTest extends UnitSuite with TestEnvironment {
 
     result should be(Success(()))
   }
+
+  test("getTranscription returns status of a transcription") {
+    val videoId                = "1"
+    val language               = "en"
+    val fakeS3Object           = mock[NdlaS3Object]
+    val fakeTranscribeResponse = mock[GetTranscriptionJobResponse]
+    val fakeJob                = mock[TranscriptionJob]
+    val fakeJobStatus          = mock[TranscriptionJobStatus]
+    when(s3TranscribeClient.getObject(any)).thenReturn(Success(fakeS3Object))
+
+    when(fakeJob.transcriptionJobStatus()).thenReturn(fakeJobStatus)
+    when(fakeTranscribeResponse.transcriptionJob()).thenReturn(fakeJob)
+    when(transcribeClient.getTranscriptionJob(any)).thenReturn(Success(fakeTranscribeResponse))
+
+    val result = transcriptionService.getTranscription(videoId, language)
+
+    result should be(Success(fakeJobStatus.toString))
+  }
+
+  test("transcribeVideo returns Success when transcription is started") {
+    val videoId            = "1"
+    val language           = "no-NO"
+    val maxSpeakers        = 2
+    val fakeS3Object       = mock[NdlaS3Object]
+    val fakeTranscribeMock = mock[StartTranscriptionJobResponse]
+    when(s3TranscribeClient.getObject(any)).thenReturn(Success(fakeS3Object))
+    when(transcriptionService.getAudioExtractionStatus(videoId, language)).thenReturn(Success(()))
+    when(transcribeClient.startTranscriptionJob(any, any, any, any, any, any, any, any))
+      .thenReturn(Success(fakeTranscribeMock))
+    val result = transcriptionService.transcribeVideo(videoId, language, maxSpeakers)
+
+    result should be(Success(()))
+  }
+
 }

From 461940ce99f4429038f66692a074eda2f592dd7c Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Thu, 12 Dec 2024 13:49:35 +0100
Subject: [PATCH 08/31] remove unused import

---
 .../no/ndla/audioapi/service/TranscriptionServiceTest.scala     | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
index 2976f15c1..d8d1ce258 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
@@ -11,7 +11,7 @@ import software.amazon.awssdk.services.transcribe.model.{
   TranscriptionJobStatus
 }
 
-import scala.util.{Failure, Success, Try}
+import scala.util.Success
 
 class TranscriptionServiceTest extends UnitSuite with TestEnvironment {
   override val transcriptionService: TranscriptionService = new TranscriptionService

From 2337237cb7912acaadc7f109c800f9b16f016666 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Fri, 13 Dec 2024 08:14:50 +0100
Subject: [PATCH 09/31] Add 400 if job already exist

---
 .../controller/TranscriptionController.scala         |  5 ++++-
 .../scala/no/ndla/audioapi/model/api/Error.scala     |  2 ++
 .../ndla/audioapi/service/TranscriptionService.scala | 12 ++++++++++++
 .../no/ndla/network/tapir/TapirErrorHandling.scala   |  1 +
 4 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index ea2344344..e11967e30 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -1,6 +1,7 @@
 package no.ndla.audioapi.controller
 
 import no.ndla.audioapi.Props
+import no.ndla.audioapi.model.api.JobAlreadyFoundException
 import no.ndla.audioapi.service.{ReadService, TranscriptionService}
 import no.ndla.network.tapir.TapirController
 import no.ndla.network.tapir.TapirUtil.errorOutputsFor
@@ -68,7 +69,9 @@ trait TranscriptionController {
       .serverLogicPure { _ =>
         { case (videoId, language, maxSpeakerOpt) =>
           transcriptionService.transcribeVideo(videoId, language, maxSpeakerOpt) match {
-            case Success(_)  => Right(())
+            case Success(_) => Right(())
+            case Failure(ex: JobAlreadyFoundException) =>
+              returnLeftError(ex)
             case Failure(ex) => returnLeftError(ex)
           }
         }
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/model/api/Error.scala b/audio-api/src/main/scala/no/ndla/audioapi/model/api/Error.scala
index 9ff4fad79..2548d19af 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/model/api/Error.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/model/api/Error.scala
@@ -55,6 +55,7 @@ trait ErrorHandling extends TapirErrorHandling {
         if rf.error.rootCause
           .exists(x => x.`type` == "search_context_missing_exception" || x.reason == "Cannot parse scroll id") =>
       invalidSearchContext
+    case jafe: JobAlreadyFoundException => ErrorBody(JOB_ALREADY_FOUND, jafe.getMessage, clock.now(), 400)
   }
 
 }
@@ -64,3 +65,4 @@ case class CouldNotFindLanguageException(message: String) extends RuntimeExcepti
 class AudioStorageException(message: String)              extends RuntimeException(message)
 class LanguageMappingException(message: String)           extends RuntimeException(message)
 class ImportException(message: String)                    extends RuntimeException(message)
+case class JobAlreadyFoundException(message: String)      extends RuntimeException(message)
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index d197cc1c2..3eb2e7b5c 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -2,6 +2,7 @@ package no.ndla.audioapi.service
 
 import com.typesafe.scalalogging.StrictLogging
 import no.ndla.audioapi.Props
+import no.ndla.audioapi.model.api.JobAlreadyFoundException
 import no.ndla.common.aws.{NdlaAWSTranscribeClient, NdlaS3Client}
 import no.ndla.common.brightcove.NdlaBrightcoveClient
 import sttp.client3.{HttpURLConnectionBackend, UriContext, asFile, basicRequest}
@@ -19,6 +20,17 @@ trait TranscriptionService {
   class TranscriptionService extends StrictLogging {
 
     def transcribeVideo(videoId: String, language: String, maxSpeakers: Int): Try[Unit] = {
+      getTranscription(videoId, language) match {
+        case Success(status) if status == "COMPLETED" =>
+          logger.info(s"Transcription already completed for videoId: $videoId")
+          return Failure(new JobAlreadyFoundException(s"Transcription already completed for videoId: $videoId"))
+        case Success(status) if status == "IN_PROGRESS" =>
+          logger.info(s"Transcription already in progress for videoId: $videoId")
+          return Failure(new JobAlreadyFoundException(s"Transcription already in progress for videoId: $videoId"))
+        case _ =>
+          logger.info(s"No existing transcription job for videoId: $videoId")
+      }
+
       getAudioExtractionStatus(videoId, language) match {
         case Success(_) =>
           logger.info(s"Audio already extracted for videoId: $videoId")
diff --git a/network/src/main/scala/no/ndla/network/tapir/TapirErrorHandling.scala b/network/src/main/scala/no/ndla/network/tapir/TapirErrorHandling.scala
index 9c7fb791a..066b249b5 100644
--- a/network/src/main/scala/no/ndla/network/tapir/TapirErrorHandling.scala
+++ b/network/src/main/scala/no/ndla/network/tapir/TapirErrorHandling.scala
@@ -78,6 +78,7 @@ trait TapirErrorHandling extends StrictLogging {
     val VALIDATION             = "VALIDATION_ERROR"
     val METHOD_NOT_ALLOWED     = "METHOD_NOT_ALLOWED"
     val CONFLICT               = "CONFLICT"
+    val JOB_ALREADY_FOUND      = "JOB_ALREADY_FOUND"
 
     val PARAMETER_MISSING      = "PARAMETER MISSING"
     val PROVIDER_NOT_SUPPORTED = "PROVIDER NOT SUPPORTED"

From 5cdb3310b26cc0c5045ddff51f69f3779d51bbfa Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Fri, 13 Dec 2024 08:30:01 +0100
Subject: [PATCH 10/31] Clean up folder names and logs

---
 .../no/ndla/audioapi/service/TranscriptionService.scala   | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index 3eb2e7b5c..7d6d463f9 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -45,7 +45,7 @@ trait TranscriptionService {
           }
       }
 
-      val audioUri = s"s3://${props.TranscribeStorageName}/audio/$language/$videoId.mp3"
+      val audioUri = s"s3://${props.TranscribeStorageName}/audio-extraction/$language/$videoId.mp3"
       logger.info(s"Transcribing audio from: $audioUri")
       val jobName      = s"transcription-$videoId-$language"
       val mediaFormat  = "mp3"
@@ -103,8 +103,7 @@ trait TranscriptionService {
         encoder.encode(new MultimediaObject(videoFile), audioFile, encodingAttributes)
       } match {
         case Success(_) =>
-          logger.info("dasjhkdaidashjdas")
-          val s3Key = s"audio/$language/$videoId.mp3"
+          val s3Key = s"audio-extraction/$language/$videoId.mp3"
           logger.info(s"Uploading audio file to S3: $s3Key")
           s3TranscribeClient.putObject(s3Key, audioFile, "audio/mpeg") match {
             case Success(_) =>
@@ -117,12 +116,11 @@ trait TranscriptionService {
               Failure(new RuntimeException(s"Failed to upload audio file to S3.", ex))
           }
         case Failure(exception) => Failure(exception)
-
       }
     }
 
     def getAudioExtractionStatus(videoId: String, language: String): Try[Unit] = {
-      s3TranscribeClient.getObject(s"audio/$language/${videoId}.mp3") match {
+      s3TranscribeClient.getObject(s"audio-extraction/$language/${videoId}.mp3") match {
         case Success(_)         => Success(())
         case Failure(exception) => Failure(exception)
       }

From d6e64b2b24fdac56b8c861437d9ca5f456849787 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Fri, 13 Dec 2024 10:02:48 +0100
Subject: [PATCH 11/31] Update descriptions of transcription endpoints

---
 .../no/ndla/audioapi/controller/TranscriptionController.scala | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index e11967e30..f0068b747 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -60,7 +60,7 @@ trait TranscriptionController {
 
     def postTranscription: ServerEndpoint[Any, Eff] = endpoint.post
       .summary("Transcribe video")
-      .description("Transcribes a video to a specific language, and uploads the transcription to S3.")
+      .description("Transcribes a video and uploads the transcription to S3.")
       .in(videoId)
       .in(language)
       .in(maxSpeaker)
@@ -78,7 +78,7 @@ trait TranscriptionController {
       }
 
     def getTranscription: ServerEndpoint[Any, Eff] = endpoint.get
-      .summary("Get transcription")
+      .summary("Get the transcription status of a video")
       .description("Get the transcription of a video.")
       .in(videoId)
       .in(language)

From 47834f40fbe6f366f93f450874c83e78ef117bbf Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 16 Dec 2024 09:41:07 +0100
Subject: [PATCH 12/31] Update function to send subtitles as response if Get
 returns 200

---
 .../controller/TranscriptionController.scala  |  9 +++--
 .../service/TranscriptionService.scala        | 34 ++++++++++++++-----
 2 files changed, 33 insertions(+), 10 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index f0068b747..d675ec62e 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -6,9 +6,11 @@ import no.ndla.audioapi.service.{ReadService, TranscriptionService}
 import no.ndla.network.tapir.TapirController
 import no.ndla.network.tapir.TapirUtil.errorOutputsFor
 import no.ndla.network.tapir.auth.Permission.DRAFT_API_WRITE
+import software.amazon.awssdk.services.transcribe.model.TranscriptionJobStatus
 import sttp.tapir.server.ServerEndpoint
 import sttp.tapir.{EndpointInput, endpoint, path}
 import sttp.tapir.*
+import sttp.tapir.json.circe.jsonBody
 
 import scala.util.{Failure, Success}
 trait TranscriptionController {
@@ -82,12 +84,15 @@ trait TranscriptionController {
       .description("Get the transcription of a video.")
       .in(videoId)
       .in(language)
-      .errorOut(errorOutputsFor(400, 404, 500))
+      .errorOut(errorOutputsFor(400, 404, 405, 500))
+      .out(stringBody)
       .requirePermission(DRAFT_API_WRITE)
       .serverLogicPure { _ =>
         { case (videoId, language) =>
           transcriptionService.getTranscription(videoId, language) match {
-            case Success(_)                          => Right(())
+            case Success(Right(transcriptionContent)) => Right(transcriptionContent)
+            case Success(Left(jobStatus)) =>
+              Right(jobStatus.toString)
             case Failure(ex: NoSuchElementException) => returnLeftError(ex)
             case Failure(ex)                         => returnLeftError(ex)
           }
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index 7d6d463f9..aeb07ec4c 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -21,12 +21,14 @@ trait TranscriptionService {
 
     def transcribeVideo(videoId: String, language: String, maxSpeakers: Int): Try[Unit] = {
       getTranscription(videoId, language) match {
-        case Success(status) if status == "COMPLETED" =>
+        case Success(Right(string)) =>
           logger.info(s"Transcription already completed for videoId: $videoId")
           return Failure(new JobAlreadyFoundException(s"Transcription already completed for videoId: $videoId"))
-        case Success(status) if status == "IN_PROGRESS" =>
+        case Success(Left("IN_PROGRESS")) =>
           logger.info(s"Transcription already in progress for videoId: $videoId")
           return Failure(new JobAlreadyFoundException(s"Transcription already in progress for videoId: $videoId"))
+        case Success(Left(_)) =>
+          logger.info(s"Error occurred while checking transcription status for videoId")
         case _ =>
           logger.info(s"No existing transcription job for videoId: $videoId")
       }
@@ -47,7 +49,7 @@ trait TranscriptionService {
 
       val audioUri = s"s3://${props.TranscribeStorageName}/audio-extraction/$language/$videoId.mp3"
       logger.info(s"Transcribing audio from: $audioUri")
-      val jobName      = s"transcription-$videoId-$language"
+      val jobName      = s"transcribe-$videoId-$language"
       val mediaFormat  = "mp3"
       val outputKey    = s"transcription/$language/$videoId"
       val languageCode = language
@@ -69,12 +71,28 @@ trait TranscriptionService {
       }
     }
 
-    def getTranscription(videoId: String, language: String): Try[String] = {
-      val jobName = s"transcription-$videoId-$language"
+    def getTranscription(
+        videoId: String,
+        language: String,
+        subtitles: Boolean = true
+    ): Try[Either[String, String]] = {
+      val jobName = s"transcribe-$videoId-$language"
 
-      transcribeClient.getTranscriptionJob(jobName).map { transcriptionJobResponse =>
-        val transcriptionJobStatus = transcriptionJobResponse.transcriptionJob().transcriptionJobStatus()
-        transcriptionJobStatus.toString
+      transcribeClient.getTranscriptionJob(jobName).flatMap { transcriptionJobResponse =>
+        val transcriptionJob       = transcriptionJobResponse.transcriptionJob()
+        val transcriptionJobStatus = transcriptionJob.transcriptionJobStatus().toString
+
+        if (transcriptionJobStatus == "COMPLETED") {
+          val transcribeUri = s"transcription/$language/${videoId}" + (if (subtitles) ".vtt" else "")
+
+          s3TranscribeClient.getObject(transcribeUri).map { s3Object =>
+            val content = scala.io.Source.fromInputStream(s3Object.stream).mkString
+            s3Object.stream.close()
+            Right(content)
+          }
+        } else {
+          Success(Left(transcriptionJobStatus))
+        }
       }
     }
 

From 493e7f137dd15921757ce4cbc3424157da54044d Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 16 Dec 2024 09:53:40 +0100
Subject: [PATCH 13/31] Remove unused imports

---
 .../no/ndla/audioapi/controller/TranscriptionController.scala   | 2 --
 1 file changed, 2 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index d675ec62e..52025f04c 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -6,11 +6,9 @@ import no.ndla.audioapi.service.{ReadService, TranscriptionService}
 import no.ndla.network.tapir.TapirController
 import no.ndla.network.tapir.TapirUtil.errorOutputsFor
 import no.ndla.network.tapir.auth.Permission.DRAFT_API_WRITE
-import software.amazon.awssdk.services.transcribe.model.TranscriptionJobStatus
 import sttp.tapir.server.ServerEndpoint
 import sttp.tapir.{EndpointInput, endpoint, path}
 import sttp.tapir.*
-import sttp.tapir.json.circe.jsonBody
 
 import scala.util.{Failure, Success}
 trait TranscriptionController {

From 0342b7fd24936b5e79c494435fab78140deefa36 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 16 Dec 2024 10:25:25 +0100
Subject: [PATCH 14/31] Add json return for transcription results

---
 .../controller/TranscriptionController.scala      | 11 +++++++----
 .../model/api/TranscriptionResultDTO.scala        | 15 +++++++++++++++
 .../audioapi/service/TranscriptionService.scala   |  5 ++---
 3 files changed, 24 insertions(+), 7 deletions(-)
 create mode 100644 audio-api/src/main/scala/no/ndla/audioapi/model/api/TranscriptionResultDTO.scala

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index 52025f04c..881d7d9a9 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -1,14 +1,16 @@
 package no.ndla.audioapi.controller
 
 import no.ndla.audioapi.Props
-import no.ndla.audioapi.model.api.JobAlreadyFoundException
+import no.ndla.audioapi.model.api.{JobAlreadyFoundException, TranscriptionResultDTO}
 import no.ndla.audioapi.service.{ReadService, TranscriptionService}
+import no.ndla.network.tapir.NoNullJsonPrinter.jsonBody
 import no.ndla.network.tapir.TapirController
 import no.ndla.network.tapir.TapirUtil.errorOutputsFor
 import no.ndla.network.tapir.auth.Permission.DRAFT_API_WRITE
 import sttp.tapir.server.ServerEndpoint
 import sttp.tapir.{EndpointInput, endpoint, path}
 import sttp.tapir.*
+import sttp.tapir.generic.auto.schemaForCaseClass
 
 import scala.util.{Failure, Success}
 trait TranscriptionController {
@@ -83,14 +85,15 @@ trait TranscriptionController {
       .in(videoId)
       .in(language)
       .errorOut(errorOutputsFor(400, 404, 405, 500))
-      .out(stringBody)
+      .out(jsonBody[TranscriptionResultDTO])
       .requirePermission(DRAFT_API_WRITE)
       .serverLogicPure { _ =>
         { case (videoId, language) =>
           transcriptionService.getTranscription(videoId, language) match {
-            case Success(Right(transcriptionContent)) => Right(transcriptionContent)
+            case Success(Right(transcriptionContent)) =>
+              Right(TranscriptionResultDTO("COMPLETED", Some(transcriptionContent)))
             case Success(Left(jobStatus)) =>
-              Right(jobStatus.toString)
+              Right(TranscriptionResultDTO(jobStatus.toString, None))
             case Failure(ex: NoSuchElementException) => returnLeftError(ex)
             case Failure(ex)                         => returnLeftError(ex)
           }
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/model/api/TranscriptionResultDTO.scala b/audio-api/src/main/scala/no/ndla/audioapi/model/api/TranscriptionResultDTO.scala
new file mode 100644
index 000000000..106abc93c
--- /dev/null
+++ b/audio-api/src/main/scala/no/ndla/audioapi/model/api/TranscriptionResultDTO.scala
@@ -0,0 +1,15 @@
+package no.ndla.audioapi.model.api
+
+import io.circe.generic.semiauto.{deriveDecoder, deriveEncoder}
+import io.circe.{Decoder, Encoder}
+import sttp.tapir.Schema.annotations.description
+
+@description("The result of a transcription job")
+case class TranscriptionResultDTO(
+    @description("The status of the transcription job") status: String,
+    @description("The transcription of the audio") transcription: Option[String]
+)
+object TranscriptionResultDTO {
+  implicit val encoder: Encoder[TranscriptionResultDTO] = deriveEncoder
+  implicit val decoder: Decoder[TranscriptionResultDTO] = deriveDecoder
+}
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index aeb07ec4c..aa12a5ae0 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -73,8 +73,7 @@ trait TranscriptionService {
 
     def getTranscription(
         videoId: String,
-        language: String,
-        subtitles: Boolean = true
+        language: String
     ): Try[Either[String, String]] = {
       val jobName = s"transcribe-$videoId-$language"
 
@@ -83,7 +82,7 @@ trait TranscriptionService {
         val transcriptionJobStatus = transcriptionJob.transcriptionJobStatus().toString
 
         if (transcriptionJobStatus == "COMPLETED") {
-          val transcribeUri = s"transcription/$language/${videoId}" + (if (subtitles) ".vtt" else "")
+          val transcribeUri = s"transcription/$language/${videoId}.vtt"
 
           s3TranscribeClient.getObject(transcribeUri).map { s3Object =>
             val content = scala.io.Source.fromInputStream(s3Object.stream).mkString

From 7d7e95eee11d10ff6c0b09c1af1661ff25e8865a Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 16 Dec 2024 10:34:45 +0100
Subject: [PATCH 15/31] Fix syntax error

---
 .../scala/no/ndla/audioapi/service/TranscriptionService.scala   | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index aa12a5ae0..acb5dfc6c 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -21,7 +21,7 @@ trait TranscriptionService {
 
     def transcribeVideo(videoId: String, language: String, maxSpeakers: Int): Try[Unit] = {
       getTranscription(videoId, language) match {
-        case Success(Right(string)) =>
+        case Success(Right(_)) =>
           logger.info(s"Transcription already completed for videoId: $videoId")
           return Failure(new JobAlreadyFoundException(s"Transcription already completed for videoId: $videoId"))
         case Success(Left("IN_PROGRESS")) =>

From e0109cd059b61a396aa83fcaff22c4afe9801cf0 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 16 Dec 2024 11:35:06 +0100
Subject: [PATCH 16/31] Add mock for getting transcription results

---
 .../no/ndla/audioapi/service/TranscriptionServiceTest.scala    | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
index d8d1ce258..34f5f9080 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
@@ -47,7 +47,7 @@ class TranscriptionServiceTest extends UnitSuite with TestEnvironment {
 
     val result = transcriptionService.getTranscription(videoId, language)
 
-    result should be(Success(fakeJobStatus.toString))
+    result should be(Success(Left(fakeJobStatus.toString)))
   }
 
   test("transcribeVideo returns Success when transcription is started") {
@@ -56,6 +56,7 @@ class TranscriptionServiceTest extends UnitSuite with TestEnvironment {
     val maxSpeakers        = 2
     val fakeS3Object       = mock[NdlaS3Object]
     val fakeTranscribeMock = mock[StartTranscriptionJobResponse]
+    when(transcribeClient.getTranscriptionJob(any)).thenReturn(Success(mock[GetTranscriptionJobResponse]))
     when(s3TranscribeClient.getObject(any)).thenReturn(Success(fakeS3Object))
     when(transcriptionService.getAudioExtractionStatus(videoId, language)).thenReturn(Success(()))
     when(transcribeClient.startTranscriptionJob(any, any, any, any, any, any, any, any))

From 850dbd9e116fe4dc0d0949708b29dba15e673ca2 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Tue, 17 Dec 2024 10:23:59 +0100
Subject: [PATCH 17/31] add a temp audio endpoint

---
 .../no/ndla/audioapi/AudioApiProperties.scala |  2 +-
 .../controller/TranscriptionController.scala  | 60 ++++++++++++++++--
 .../service/TranscriptionService.scala        | 61 ++++++++++++++++++-
 .../service/TranscriptionServiceTest.scala    |  2 +-
 4 files changed, 117 insertions(+), 8 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala b/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
index 3430227d1..fb8571450 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
@@ -34,7 +34,7 @@ class AudioApiProperties extends BaseProps with DatabaseProps with StrictLogging
 
   val MaxAudioFileSizeBytes: Int = 1024 * 1024 * 100 // 100 MiB
 
-  val StorageName: String           = propOrElse("AUDIO_FILE_S3_BUCKET", s"$Environment.audio.ndla")
+  val StorageName: String = "test.audio.2.ndla" // propOrElse("AUDIO_FILE_S3_BUCKET", s"$Environment.audio.ndla")
   val StorageRegion: Option[String] = propOrNone("AUDIO_FILE_S3_BUCKET_REGION")
 
   val TranscribeStorageName: String = propOrElse("TRANSCRIBE_FILE_S3_BUCKET_NAME", s"$Environment.transcribe.ndla")
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index 881d7d9a9..552daa531 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -21,10 +21,12 @@ trait TranscriptionController {
     override val serviceName: String         = "transcription"
     override val prefix: EndpointInput[Unit] = "audio-api" / "v1" / serviceName
 
-    private val videoId  = path[String]("videoId").description("The video id to transcribe")
-    private val language = path[String]("language").description("The language to transcribe the video to")
+    private val videoId   = path[String]("videoId").description("The video id to transcribe")
+    private val audioName = path[String]("audioName").description("The audio name to transcribe")
+    private val language  = path[String]("language").description("The language to transcribe the video to")
     private val maxSpeaker =
       query[Int]("maxSpeaker").description("The maximum number of speakers in the video").default(2)
+    private val format = query[String]("format").description("The format of the audio file").default("mp3")
 
     def postExtractAudio: ServerEndpoint[Any, Eff] = endpoint.post
       .summary("Extract audio from video")
@@ -89,7 +91,50 @@ trait TranscriptionController {
       .requirePermission(DRAFT_API_WRITE)
       .serverLogicPure { _ =>
         { case (videoId, language) =>
-          transcriptionService.getTranscription(videoId, language) match {
+          transcriptionService.getVideoTranscription(videoId, language) match {
+            case Success(Right(transcriptionContent)) =>
+              Right(TranscriptionResultDTO("COMPLETED", Some(transcriptionContent)))
+            case Success(Left(jobStatus)) =>
+              Right(TranscriptionResultDTO(jobStatus.toString, None))
+            case Failure(ex: NoSuchElementException) => returnLeftError(ex)
+            case Failure(ex)                         => returnLeftError(ex)
+          }
+        }
+      }
+
+    def postAudioTranscription: ServerEndpoint[Any, Eff] = endpoint.post
+      .summary("Transcribe audio")
+      .description("Transcribes a video and uploads the transcription to S3.")
+      .in(audioName)
+      .in(language)
+      .in(maxSpeaker)
+      .in(format)
+      .in("audio")
+      .errorOut(errorOutputsFor(400, 500))
+      .requirePermission(DRAFT_API_WRITE)
+      .serverLogicPure { _ =>
+        { case (videoId, language, maxSpeakerOpt, format) =>
+          transcriptionService.transcribeAudio(videoId, language, maxSpeakerOpt, format) match {
+            case Success(_) => Right(())
+            case Failure(ex: JobAlreadyFoundException) =>
+              returnLeftError(ex)
+            case Failure(ex) => returnLeftError(ex)
+          }
+        }
+      }
+
+    def getAudioTranscription: ServerEndpoint[Any, Eff] = endpoint.get
+      .summary("Get the transcription status of a video")
+      .description("Get the transcription of a video.")
+      .in(audioName)
+      .in(language)
+      .in("audio")
+      .errorOut(errorOutputsFor(400, 404, 405, 500))
+      .out(jsonBody[TranscriptionResultDTO])
+      .requirePermission(DRAFT_API_WRITE)
+      .serverLogicPure { _ =>
+        { case (videoId, language) =>
+          transcriptionService.getAudioTranscription(videoId, language) match {
             case Success(Right(transcriptionContent)) =>
               Right(TranscriptionResultDTO("COMPLETED", Some(transcriptionContent)))
             case Success(Left(jobStatus)) =>
@@ -101,7 +146,14 @@ trait TranscriptionController {
       }
 
     override val endpoints: List[ServerEndpoint[Any, Eff]] =
-      List(postExtractAudio, getAudioExtraction, postTranscription, getTranscription)
+      List(
+        postExtractAudio,
+        getAudioExtraction,
+        postTranscription,
+        getTranscription,
+        postAudioTranscription,
+        getAudioTranscription
+      )
   }
 
 }
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index acb5dfc6c..9379a6bf8 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -20,7 +20,7 @@ trait TranscriptionService {
   class TranscriptionService extends StrictLogging {
 
     def transcribeVideo(videoId: String, language: String, maxSpeakers: Int): Try[Unit] = {
-      getTranscription(videoId, language) match {
+      getVideoTranscription(videoId, language) match {
         case Success(Right(_)) =>
           logger.info(s"Transcription already completed for videoId: $videoId")
           return Failure(new JobAlreadyFoundException(s"Transcription already completed for videoId: $videoId"))
@@ -71,7 +71,7 @@ trait TranscriptionService {
       }
     }
 
-    def getTranscription(
+    def getVideoTranscription(
         videoId: String,
         language: String
     ): Try[Either[String, String]] = {
@@ -95,6 +95,63 @@ trait TranscriptionService {
       }
     }
 
+    def transcribeAudio(audioName: String, language: String, maxSpeakers: Int, format: String): Try[Unit] = {
+      getVideoTranscription(audioName, language) match {
+        case Success(Right(_)) =>
+          logger.info(s"Transcription already completed for audio: $audioName")
+          return Failure(new JobAlreadyFoundException(s"Transcription already completed for audio: $audioName"))
+        case Success(Left("IN_PROGRESS")) =>
+          logger.info(s"Transcription already in progress for videoId: $audioName")
+          return Failure(new JobAlreadyFoundException(s"Transcription already in progress for audio: $audioName"))
+        case Success(Left(_)) =>
+          logger.info(s"Error occurred while checking transcription status for audio")
+        case _ =>
+          logger.info(s"No existing transcription job for audio name: $audioName")
+      }
+      val audioUri = s"s3://${props.StorageName}/$audioName.mp3"
+      logger.info(s"Transcribing audio from: $audioUri")
+      val jobName      = s"transcribe-$audioName-$language"
+      val mediaFormat  = format
+      val outputKey    = s"audio-transcription/$language/$audioName"
+      val languageCode = language
+
+      transcribeClient.startTranscriptionJob(
+        jobName,
+        audioUri,
+        mediaFormat,
+        languageCode,
+        props.TranscribeStorageName,
+        outputKey,
+        maxSpeakers
+      ) match {
+        case Success(_) =>
+          logger.info(s"Transcription job started for audio: $audioName")
+          Success(())
+        case Failure(exception) =>
+          Failure(new RuntimeException(s"Failed to start transcription for audio file: $audioName", exception))
+      }
+    }
+
+    def getAudioTranscription(audioName: String, language: String): Try[Either[String, String]] = {
+      val jobName = s"transcribe-$audioName-$language"
+
+      transcribeClient.getTranscriptionJob(jobName).flatMap { transcriptionJobResponse =>
+        val transcriptionJob       = transcriptionJobResponse.transcriptionJob()
+        val transcriptionJobStatus = transcriptionJob.transcriptionJobStatus().toString
+
+        if (transcriptionJobStatus == "COMPLETED") {
+          val transcribeUri = s"audio-transcription/$language/${audioName}"
+
+          s3TranscribeClient.getObject(transcribeUri).map { s3Object =>
+            val content = scala.io.Source.fromInputStream(s3Object.stream).mkString
+            s3Object.stream.close()
+            Right(content)
+          }
+        } else {
+          Success(Left(transcriptionJobStatus))
+        }
+      }
+    }
     def extractAudioFromVideo(videoId: String, language: String): Try[Unit] = {
       val accountId = props.BrightcoveAccountId
       val videoUrl = getVideo(accountId, videoId) match {
diff --git a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
index 34f5f9080..95c2c79c9 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
@@ -45,7 +45,7 @@ class TranscriptionServiceTest extends UnitSuite with TestEnvironment {
     when(fakeTranscribeResponse.transcriptionJob()).thenReturn(fakeJob)
     when(transcribeClient.getTranscriptionJob(any)).thenReturn(Success(fakeTranscribeResponse))
 
-    val result = transcriptionService.getTranscription(videoId, language)
+    val result = transcriptionService.getVideoTranscription(videoId, language)
 
     result should be(Success(Left(fakeJobStatus.toString)))
   }

From 9fb082ae583d470c245b9a81b33f97a7ad483cd5 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Tue, 17 Dec 2024 10:25:01 +0100
Subject: [PATCH 18/31] fix audioprop

---
 .../src/main/scala/no/ndla/audioapi/AudioApiProperties.scala    | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala b/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
index fb8571450..3430227d1 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
@@ -34,7 +34,7 @@ class AudioApiProperties extends BaseProps with DatabaseProps with StrictLogging
 
   val MaxAudioFileSizeBytes: Int = 1024 * 1024 * 100 // 100 MiB
 
-  val StorageName: String = "test.audio.2.ndla" // propOrElse("AUDIO_FILE_S3_BUCKET", s"$Environment.audio.ndla")
+  val StorageName: String           = propOrElse("AUDIO_FILE_S3_BUCKET", s"$Environment.audio.ndla")
   val StorageRegion: Option[String] = propOrNone("AUDIO_FILE_S3_BUCKET_REGION")
 
   val TranscribeStorageName: String = propOrElse("TRANSCRIBE_FILE_S3_BUCKET_NAME", s"$Environment.transcribe.ndla")

From 60efcd712fbc9cbd7f56d4eb0bcd2744b9323b96 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Wed, 18 Dec 2024 07:53:17 +0100
Subject: [PATCH 19/31] fix audio endpoints

---
 .../controller/TranscriptionController.scala  | 15 ++++++-----
 .../service/TranscriptionService.scala        | 27 +++++++++++--------
 project/audioapi.scala                        |  3 ++-
 3 files changed, 27 insertions(+), 18 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index 552daa531..97ddb368c 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -23,6 +23,7 @@ trait TranscriptionController {
 
     private val videoId   = path[String]("videoId").description("The video id to transcribe")
     private val audioName = path[String]("audioName").description("The audio name to transcribe")
+    private val audioId   = path[Long]("audioId").description("The audio id to transcribe")
     private val language  = path[String]("language").description("The language to transcribe the video to")
     private val maxSpeaker =
       query[Int]("maxSpeaker").description("The maximum number of speakers in the video").default(2)
@@ -105,16 +106,17 @@ trait TranscriptionController {
     def postAudioTranscription: ServerEndpoint[Any, Eff] = endpoint.post
       .summary("Transcribe audio")
       .description("Transcribes a video and uploads the transcription to S3.")
+      .in("audio")
       .in(audioName)
+      .in(audioId)
       .in(language)
       .in(maxSpeaker)
       .in(format)
-      .in("audio")
       .errorOut(errorOutputsFor(400, 500))
       .requirePermission(DRAFT_API_WRITE)
       .serverLogicPure { _ =>
-        { case (videoId, language, maxSpeakerOpt, format) =>
-          transcriptionService.transcribeAudio(videoId, language, maxSpeakerOpt, format) match {
+        { case (audioName, audioId, language, maxSpeakerOpt, format) =>
+          transcriptionService.transcribeAudio(audioName, audioId, language, maxSpeakerOpt, format) match {
             case Success(_) => Right(())
             case Failure(ex: JobAlreadyFoundException) =>
               returnLeftError(ex)
@@ -126,15 +128,16 @@ trait TranscriptionController {
     def getAudioTranscription: ServerEndpoint[Any, Eff] = endpoint.get
       .summary("Get the transcription status of a video")
       .description("Get the transcription of a video.")
+      .in("audio")
       .in(audioName)
+      .in(audioId)
       .in(language)
-      .in("audio")
       .errorOut(errorOutputsFor(400, 404, 405, 500))
       .out(jsonBody[TranscriptionResultDTO])
       .requirePermission(DRAFT_API_WRITE)
       .serverLogicPure { _ =>
-        { case (videoId, language) =>
-          transcriptionService.getAudioTranscription(videoId, language) match {
+        { case (audioName, audioId, language) =>
+          transcriptionService.getAudioTranscription(audioName, audioId, language) match {
             case Success(Right(transcriptionContent)) =>
               Right(TranscriptionResultDTO("COMPLETED", Some(transcriptionContent)))
             case Success(Left(jobStatus)) =>
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index 9379a6bf8..afb4ab9fc 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -49,7 +49,7 @@ trait TranscriptionService {
 
       val audioUri = s"s3://${props.TranscribeStorageName}/audio-extraction/$language/$videoId.mp3"
       logger.info(s"Transcribing audio from: $audioUri")
-      val jobName      = s"transcribe-$videoId-$language"
+      val jobName      = s"transcribe-video-$videoId-$language"
       val mediaFormat  = "mp3"
       val outputKey    = s"transcription/$language/$videoId"
       val languageCode = language
@@ -75,7 +75,7 @@ trait TranscriptionService {
         videoId: String,
         language: String
     ): Try[Either[String, String]] = {
-      val jobName = s"transcribe-$videoId-$language"
+      val jobName = s"transcribe-video-$videoId-$language"
 
       transcribeClient.getTranscriptionJob(jobName).flatMap { transcriptionJobResponse =>
         val transcriptionJob       = transcriptionJobResponse.transcriptionJob()
@@ -95,8 +95,14 @@ trait TranscriptionService {
       }
     }
 
-    def transcribeAudio(audioName: String, language: String, maxSpeakers: Int, format: String): Try[Unit] = {
-      getVideoTranscription(audioName, language) match {
+    def transcribeAudio(
+        audioName: String,
+        audioId: Long,
+        language: String,
+        maxSpeakers: Int,
+        format: String
+    ): Try[Unit] = {
+      getAudioTranscription(audioName, audioId, language) match {
         case Success(Right(_)) =>
           logger.info(s"Transcription already completed for audio: $audioName")
           return Failure(new JobAlreadyFoundException(s"Transcription already completed for audio: $audioName"))
@@ -108,13 +114,12 @@ trait TranscriptionService {
         case _ =>
           logger.info(s"No existing transcription job for audio name: $audioName")
       }
-      val audioUri = s"s3://${props.StorageName}/$audioName.mp3"
+      val audioUri = s"s3://${props.StorageName}/$audioName"
       logger.info(s"Transcribing audio from: $audioUri")
-      val jobName      = s"transcribe-$audioName-$language"
+      val jobName      = s"transcribe-audio-$audioId-$language"
       val mediaFormat  = format
-      val outputKey    = s"audio-transcription/$language/$audioName"
+      val outputKey    = s"audio-transcription/$language/$audioId"
       val languageCode = language
-
       transcribeClient.startTranscriptionJob(
         jobName,
         audioUri,
@@ -132,15 +137,15 @@ trait TranscriptionService {
       }
     }
 
-    def getAudioTranscription(audioName: String, language: String): Try[Either[String, String]] = {
-      val jobName = s"transcribe-$audioName-$language"
+    def getAudioTranscription(audioName: String, audioId: Long, language: String): Try[Either[String, String]] = {
+      val jobName = s"transcribe-audio-$audioId-$language"
 
       transcribeClient.getTranscriptionJob(jobName).flatMap { transcriptionJobResponse =>
         val transcriptionJob       = transcriptionJobResponse.transcriptionJob()
         val transcriptionJobStatus = transcriptionJob.transcriptionJobStatus().toString
 
         if (transcriptionJobStatus == "COMPLETED") {
-          val transcribeUri = s"audio-transcription/$language/${audioName}"
+          val transcribeUri = s"audio-transcription/$language/${audioId}"
 
           s3TranscribeClient.getObject(transcribeUri).map { s3Object =>
             val content = scala.io.Source.fromInputStream(s3Object.stream).mkString
diff --git a/project/audioapi.scala b/project/audioapi.scala
index 0e5cc75aa..5b5442375 100644
--- a/project/audioapi.scala
+++ b/project/audioapi.scala
@@ -42,7 +42,8 @@ object audioapi extends Module {
       "AudioMetaInformationDTO",
       "UpdatedAudioMetaInformationDTO",
       "SeriesSummarySearchResultDTO",
-      "SeriesSearchParamsDTO"
+      "SeriesSearchParamsDTO",
+      "TranscriptionResultDTO"
     )
   )
 

From 8a24b8d61f51d6f6c100720b32aa15de0237ce67 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Wed, 18 Dec 2024 13:07:12 +0100
Subject: [PATCH 20/31] Fix licensing and unused audioName in get call

---
 .../controller/TranscriptionController.scala        | 13 ++++++++++---
 .../audioapi/model/api/TranscriptionResultDTO.scala |  8 ++++++++
 .../audioapi/service/TranscriptionService.scala     | 10 +++++++++-
 .../audioapi/service/TranscriptionServiceTest.scala |  8 ++++++++
 .../common/brightcove/NdlaBrightcoveClient.scala    |  8 ++++++++
 5 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index 97ddb368c..76e4f8699 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -1,3 +1,11 @@
+/*
+ * Part of NDLA audio-api
+ * Copyright (C) 2024 NDLA
+ *
+ * See LICENSE
+ *
+ */
+
 package no.ndla.audioapi.controller
 
 import no.ndla.audioapi.Props
@@ -129,15 +137,14 @@ trait TranscriptionController {
       .summary("Get the transcription status of a video")
       .description("Get the transcription of a video.")
       .in("audio")
-      .in(audioName)
       .in(audioId)
       .in(language)
       .errorOut(errorOutputsFor(400, 404, 405, 500))
       .out(jsonBody[TranscriptionResultDTO])
       .requirePermission(DRAFT_API_WRITE)
       .serverLogicPure { _ =>
-        { case (audioName, audioId, language) =>
-          transcriptionService.getAudioTranscription(audioName, audioId, language) match {
+        { case (audioId, language) =>
+          transcriptionService.getAudioTranscription(audioId, language) match {
             case Success(Right(transcriptionContent)) =>
               Right(TranscriptionResultDTO("COMPLETED", Some(transcriptionContent)))
             case Success(Left(jobStatus)) =>
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/model/api/TranscriptionResultDTO.scala b/audio-api/src/main/scala/no/ndla/audioapi/model/api/TranscriptionResultDTO.scala
index 106abc93c..faf5ef5aa 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/model/api/TranscriptionResultDTO.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/model/api/TranscriptionResultDTO.scala
@@ -1,3 +1,11 @@
+/*
+ * Part of NDLA audio-api
+ * Copyright (C) 2024 NDLA
+ *
+ * See LICENSE
+ *
+ */
+
 package no.ndla.audioapi.model.api
 
 import io.circe.generic.semiauto.{deriveDecoder, deriveEncoder}
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index afb4ab9fc..e286e07a4 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -1,3 +1,11 @@
+/*
+ * Part of NDLA audio-api
+ * Copyright (C) 2024 NDLA
+ *
+ * See LICENSE
+ *
+ */
+
 package no.ndla.audioapi.service
 
 import com.typesafe.scalalogging.StrictLogging
@@ -137,7 +145,7 @@ trait TranscriptionService {
       }
     }
 
-    def getAudioTranscription(audioName: String, audioId: Long, language: String): Try[Either[String, String]] = {
+    def getAudioTranscription(audioId: Long, language: String): Try[Either[String, String]] = {
       val jobName = s"transcribe-audio-$audioId-$language"
 
       transcribeClient.getTranscriptionJob(jobName).flatMap { transcriptionJobResponse =>
diff --git a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
index 95c2c79c9..773e0061e 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
@@ -1,3 +1,11 @@
+/*
+ * Part of NDLA audio-api
+ * Copyright (C) 2024 NDLA
+ *
+ * See LICENSE
+ *
+ */
+
 package no.ndla.audioapi.service
 
 import no.ndla.audioapi.{AudioApiProperties, TestEnvironment, UnitSuite}
diff --git a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
index 135c7f399..64f1011a7 100644
--- a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
+++ b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
@@ -1,3 +1,11 @@
+/*
+ * Part of NDLA common
+ * Copyright (C) 2024 NDLA
+ *
+ * See LICENSE
+ *
+ */
+
 package no.ndla.common.brightcove
 
 import io.circe.Json

From e54886d753e3703929cc9c995f48493504c0cee0 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Wed, 18 Dec 2024 14:58:30 +0100
Subject: [PATCH 21/31] Make creation of subtitle file optional

---
 .../service/TranscriptionService.scala        | 26 ++++++++++---------
 .../common/aws/NdlaAWSTranscribeClient.scala  | 11 +++++---
 2 files changed, 21 insertions(+), 16 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index e286e07a4..46121c452 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -92,11 +92,7 @@ trait TranscriptionService {
         if (transcriptionJobStatus == "COMPLETED") {
           val transcribeUri = s"transcription/$language/${videoId}.vtt"
 
-          s3TranscribeClient.getObject(transcribeUri).map { s3Object =>
-            val content = scala.io.Source.fromInputStream(s3Object.stream).mkString
-            s3Object.stream.close()
-            Right(content)
-          }
+          getObjectFromS3(transcribeUri)
         } else {
           Success(Left(transcriptionJobStatus))
         }
@@ -110,7 +106,7 @@ trait TranscriptionService {
         maxSpeakers: Int,
         format: String
     ): Try[Unit] = {
-      getAudioTranscription(audioName, audioId, language) match {
+      getAudioTranscription(audioId, language) match {
         case Success(Right(_)) =>
           logger.info(s"Transcription already completed for audio: $audioName")
           return Failure(new JobAlreadyFoundException(s"Transcription already completed for audio: $audioName"))
@@ -135,7 +131,8 @@ trait TranscriptionService {
         languageCode,
         props.TranscribeStorageName,
         outputKey,
-        maxSpeakers
+        maxSpeakers,
+        includeSubtitles = false
       ) match {
         case Success(_) =>
           logger.info(s"Transcription job started for audio: $audioName")
@@ -155,16 +152,21 @@ trait TranscriptionService {
         if (transcriptionJobStatus == "COMPLETED") {
           val transcribeUri = s"audio-transcription/$language/${audioId}"
 
-          s3TranscribeClient.getObject(transcribeUri).map { s3Object =>
-            val content = scala.io.Source.fromInputStream(s3Object.stream).mkString
-            s3Object.stream.close()
-            Right(content)
-          }
+          getObjectFromS3(transcribeUri)
         } else {
           Success(Left(transcriptionJobStatus))
         }
       }
     }
+
+    private def getObjectFromS3(Uri: String): Try[Either[String, String]] = {
+      s3TranscribeClient.getObject(Uri).map { s3Object =>
+        val content = scala.io.Source.fromInputStream(s3Object.stream).mkString
+        s3Object.stream.close()
+        Right(content)
+      }
+    }
+
     def extractAudioFromVideo(videoId: String, language: String): Try[Unit] = {
       val accountId = props.BrightcoveAccountId
       val videoUrl = getVideo(accountId, videoId) match {
diff --git a/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala b/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
index 3ba02563f..3704c86dc 100644
--- a/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
+++ b/common/src/main/scala/no/ndla/common/aws/NdlaAWSTranscribeClient.scala
@@ -32,9 +32,10 @@ trait NdlaAWSTranscribeClient {
         outputBucket: String,
         outputKey: String,
         maxSpeakers: Int,
+        includeSubtitles: Boolean = true,
         outputSubtitleFormat: String = "VTT"
     ): Try[StartTranscriptionJobResponse] = Try {
-      val request = StartTranscriptionJobRequest
+      val requestBuilder = StartTranscriptionJobRequest
         .builder()
         .transcriptionJobName(jobName)
         .media(Media.builder().mediaFileUri(mediaUri).build())
@@ -49,15 +50,17 @@ trait NdlaAWSTranscribeClient {
             .maxSpeakerLabels(maxSpeakers)
             .build()
         )
-        .subtitles(
+
+      if (includeSubtitles) {
+        requestBuilder.subtitles(
           Subtitles
             .builder()
             .formats(SubtitleFormat.valueOf(outputSubtitleFormat))
             .build()
         )
-        .build()
+      }
 
-      client.startTranscriptionJob(request)
+      client.startTranscriptionJob(requestBuilder.build())
     }
 
     def getTranscriptionJob(jobName: String): Try[GetTranscriptionJobResponse] = {

From 31b918ef2cd2760b3e8e250bab505919aad4e08c Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Wed, 18 Dec 2024 15:07:45 +0100
Subject: [PATCH 22/31] fix test

---
 .../no/ndla/audioapi/service/TranscriptionServiceTest.scala     | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
index 773e0061e..8d64d3678 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/service/TranscriptionServiceTest.scala
@@ -67,7 +67,7 @@ class TranscriptionServiceTest extends UnitSuite with TestEnvironment {
     when(transcribeClient.getTranscriptionJob(any)).thenReturn(Success(mock[GetTranscriptionJobResponse]))
     when(s3TranscribeClient.getObject(any)).thenReturn(Success(fakeS3Object))
     when(transcriptionService.getAudioExtractionStatus(videoId, language)).thenReturn(Success(()))
-    when(transcribeClient.startTranscriptionJob(any, any, any, any, any, any, any, any))
+    when(transcribeClient.startTranscriptionJob(any, any, any, any, any, any, any, any, any))
       .thenReturn(Success(fakeTranscribeMock))
     val result = transcriptionService.transcribeVideo(videoId, language, maxSpeakers)
 

From 5163c808dfb972548160264f65d10417b5d265d1 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Fri, 20 Dec 2024 13:01:43 +0100
Subject: [PATCH 23/31] Update permissions and descriptions, refactor to
 existing s3 putobject

---
 .../controller/TranscriptionController.scala  | 24 ++++++++--------
 .../service/TranscriptionService.scala        | 10 ++++++-
 .../no/ndla/common/aws/NdlaS3Client.scala     | 28 -------------------
 typescript/types-backend/audio-api.ts         |  5 ++++
 4 files changed, 27 insertions(+), 40 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index 76e4f8699..d49beb040 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -14,7 +14,7 @@ import no.ndla.audioapi.service.{ReadService, TranscriptionService}
 import no.ndla.network.tapir.NoNullJsonPrinter.jsonBody
 import no.ndla.network.tapir.TapirController
 import no.ndla.network.tapir.TapirUtil.errorOutputsFor
-import no.ndla.network.tapir.auth.Permission.DRAFT_API_WRITE
+import no.ndla.network.tapir.auth.Permission.AUDIO_API_WRITE
 import sttp.tapir.server.ServerEndpoint
 import sttp.tapir.{EndpointInput, endpoint, path}
 import sttp.tapir.*
@@ -32,7 +32,7 @@ trait TranscriptionController {
     private val videoId   = path[String]("videoId").description("The video id to transcribe")
     private val audioName = path[String]("audioName").description("The audio name to transcribe")
     private val audioId   = path[Long]("audioId").description("The audio id to transcribe")
-    private val language  = path[String]("language").description("The language to transcribe the video to")
+    private val language  = path[String]("language").description("The language to run the transcription in")
     private val maxSpeaker =
       query[Int]("maxSpeaker").description("The maximum number of speakers in the video").default(2)
     private val format = query[String]("format").description("The format of the audio file").default("mp3")
@@ -44,7 +44,7 @@ trait TranscriptionController {
       .in(language)
       .in("extract-audio")
       .errorOut(errorOutputsFor(400, 500))
-      .requirePermission(DRAFT_API_WRITE)
+      .requirePermission(AUDIO_API_WRITE)
       .serverLogicPure { _ =>
         { case (videoId, language) =>
           transcriptionService.extractAudioFromVideo(videoId, language) match {
@@ -61,7 +61,7 @@ trait TranscriptionController {
       .in(language)
       .in("extract-audio")
       .errorOut(errorOutputsFor(400, 500))
-      .requirePermission(DRAFT_API_WRITE)
+      .requirePermission(AUDIO_API_WRITE)
       .serverLogicPure { _ =>
         { case (videoId, language) =>
           transcriptionService.getAudioExtractionStatus(videoId, language) match {
@@ -74,11 +74,12 @@ trait TranscriptionController {
     def postTranscription: ServerEndpoint[Any, Eff] = endpoint.post
       .summary("Transcribe video")
       .description("Transcribes a video and uploads the transcription to S3.")
+      .in("video")
       .in(videoId)
       .in(language)
       .in(maxSpeaker)
       .errorOut(errorOutputsFor(400, 500))
-      .requirePermission(DRAFT_API_WRITE)
+      .requirePermission(AUDIO_API_WRITE)
       .serverLogicPure { _ =>
         { case (videoId, language, maxSpeakerOpt) =>
           transcriptionService.transcribeVideo(videoId, language, maxSpeakerOpt) match {
@@ -93,11 +94,12 @@ trait TranscriptionController {
     def getTranscription: ServerEndpoint[Any, Eff] = endpoint.get
       .summary("Get the transcription status of a video")
       .description("Get the transcription of a video.")
+      .in("video")
       .in(videoId)
       .in(language)
       .errorOut(errorOutputsFor(400, 404, 405, 500))
       .out(jsonBody[TranscriptionResultDTO])
-      .requirePermission(DRAFT_API_WRITE)
+      .requirePermission(AUDIO_API_WRITE)
       .serverLogicPure { _ =>
         { case (videoId, language) =>
           transcriptionService.getVideoTranscription(videoId, language) match {
@@ -113,7 +115,7 @@ trait TranscriptionController {
 
     def postAudioTranscription: ServerEndpoint[Any, Eff] = endpoint.post
       .summary("Transcribe audio")
-      .description("Transcribes a video and uploads the transcription to S3.")
+      .description("Transcribes an audiofile and uploads the transcription to S3.")
       .in("audio")
       .in(audioName)
       .in(audioId)
@@ -121,7 +123,7 @@ trait TranscriptionController {
       .in(maxSpeaker)
       .in(format)
       .errorOut(errorOutputsFor(400, 500))
-      .requirePermission(DRAFT_API_WRITE)
+      .requirePermission(AUDIO_API_WRITE)
       .serverLogicPure { _ =>
         { case (audioName, audioId, language, maxSpeakerOpt, format) =>
           transcriptionService.transcribeAudio(audioName, audioId, language, maxSpeakerOpt, format) match {
@@ -134,14 +136,14 @@ trait TranscriptionController {
       }
 
     def getAudioTranscription: ServerEndpoint[Any, Eff] = endpoint.get
-      .summary("Get the transcription status of a video")
-      .description("Get the transcription of a video.")
+      .summary("Get the transcription status of an audiofile")
+      .description("Get the transcription of an audiofile .")
       .in("audio")
       .in(audioId)
       .in(language)
       .errorOut(errorOutputsFor(400, 404, 405, 500))
       .out(jsonBody[TranscriptionResultDTO])
-      .requirePermission(DRAFT_API_WRITE)
+      .requirePermission(AUDIO_API_WRITE)
       .serverLogicPure { _ =>
         { case (audioId, language) =>
           transcriptionService.getAudioTranscription(audioId, language) match {
diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index 46121c452..eb916823a 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -13,6 +13,7 @@ import no.ndla.audioapi.Props
 import no.ndla.audioapi.model.api.JobAlreadyFoundException
 import no.ndla.common.aws.{NdlaAWSTranscribeClient, NdlaS3Client}
 import no.ndla.common.brightcove.NdlaBrightcoveClient
+import no.ndla.common.model.domain.UploadedFile
 import sttp.client3.{HttpURLConnectionBackend, UriContext, asFile, basicRequest}
 import ws.schild.jave.{Encoder, MultimediaObject}
 import ws.schild.jave.encode.{AudioAttributes, EncodingAttributes}
@@ -194,7 +195,14 @@ trait TranscriptionService {
         case Success(_) =>
           val s3Key = s"audio-extraction/$language/$videoId.mp3"
           logger.info(s"Uploading audio file to S3: $s3Key")
-          s3TranscribeClient.putObject(s3Key, audioFile, "audio/mpeg") match {
+          val uploadedFile = UploadedFile( // convert to uploadedFile object
+            partName = "",
+            fileName = Some(s"audio_$videoId.mp3"),
+            fileSize = audioFile.length(),
+            contentType = Some("audio/mpeg"),
+            file = audioFile
+          )
+          s3TranscribeClient.putObject(s3Key, uploadedFile) match {
             case Success(_) =>
               logger.info(s"Audio file uploaded to S3: $s3Key")
               for {
diff --git a/common/src/main/scala/no/ndla/common/aws/NdlaS3Client.scala b/common/src/main/scala/no/ndla/common/aws/NdlaS3Client.scala
index f8a7e43a2..8803eb385 100644
--- a/common/src/main/scala/no/ndla/common/aws/NdlaS3Client.scala
+++ b/common/src/main/scala/no/ndla/common/aws/NdlaS3Client.scala
@@ -13,7 +13,6 @@ import software.amazon.awssdk.regions.Region
 import software.amazon.awssdk.services.s3.model.*
 import software.amazon.awssdk.services.s3.{S3Client, S3ClientBuilder}
 
-import java.io.File
 import scala.util.Try
 
 trait NdlaS3Client {
@@ -82,33 +81,6 @@ trait NdlaS3Client {
       )
     }
 
-    def putObject(
-        key: String,
-        file: File,
-        contentType: String,
-        cacheControl: Option[String] = None
-    ): Try[PutObjectResponse] = Try {
-
-      val por = PutObjectRequest
-        .builder()
-        .bucket(bucket)
-        .key(key)
-        .contentLength(file.length())
-        .contentType(contentType)
-
-      val porWithCacheControl = cacheControl match {
-        case Some(value) => por.cacheControl(value)
-        case None        => por
-      }
-
-      val requestBody = RequestBody.fromFile(file)
-
-      client.putObject(
-        porWithCacheControl.build(),
-        requestBody
-      )
-    }
-
     def updateMetadata(key: String, metadata: java.util.Map[String, String]): Try[_] = Try {
       val cor =
         CopyObjectRequest
diff --git a/typescript/types-backend/audio-api.ts b/typescript/types-backend/audio-api.ts
index c53e0c2ad..a31ed95b7 100644
--- a/typescript/types-backend/audio-api.ts
+++ b/typescript/types-backend/audio-api.ts
@@ -196,6 +196,11 @@ export interface ITitleDTO {
   language: string
 }
 
+export interface ITranscriptionResultDTO {
+  status: string
+  transcription?: string
+}
+
 export interface IUpdatedAudioMetaInformationDTO {
   revision: number
   title: string

From 5759c2d4f8a763e3dcbf6dadf124882557bfa801 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Thu, 2 Jan 2025 08:13:50 +0100
Subject: [PATCH 24/31] Put urls into props

---
 .../no/ndla/common/brightcove/NdlaBrightcoveClient.scala  | 6 ++++--
 .../scala/no/ndla/common/configuration/BaseProps.scala    | 8 ++++++++
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
index 64f1011a7..592848d19 100644
--- a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
+++ b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
@@ -12,14 +12,16 @@ import io.circe.Json
 import io.circe.generic.codec.DerivedAsObjectCodec.deriveCodec
 import io.circe.parser.*
 import sttp.client3.{HttpClientSyncBackend, UriContext, basicRequest}
+import no.ndla.common.configuration.HasBaseProps
 
 case class TokenResponse(access_token: String, token_type: String, expires_in: Int)
 
 trait NdlaBrightcoveClient {
+  this: HasBaseProps =>
   val brightcoveClient: NdlaBrightcoveClient
 
   class NdlaBrightcoveClient {
-    private val authUrl = "https://oauth.brightcove.com/v4/access_token"
+    private val authUrl = props.brightCoveAuthUri
     private val backend = HttpClientSyncBackend() // Or AsyncHttpClientFutureBackend()
 
     def getToken(clientID: String, clientSecret: String): Either[String, String] = {
@@ -41,7 +43,7 @@ trait NdlaBrightcoveClient {
 
     def getVideoSource(accountId: String, videoId: String, bearerToken: String): Either[String, Vector[Json]] = {
 
-      val videoSourceUrl = uri"https://cms.api.brightcove.com/v1/accounts/$accountId/videos/$videoId/sources"
+      val videoSourceUrl = props.brightCoveVideoUri(accountId, videoId)
       val request = basicRequest
         .header("Authorization", s"Bearer $bearerToken")
         .get(videoSourceUrl)
diff --git a/common/src/main/scala/no/ndla/common/configuration/BaseProps.scala b/common/src/main/scala/no/ndla/common/configuration/BaseProps.scala
index 556cc52f6..6889bb36e 100644
--- a/common/src/main/scala/no/ndla/common/configuration/BaseProps.scala
+++ b/common/src/main/scala/no/ndla/common/configuration/BaseProps.scala
@@ -1,5 +1,8 @@
 package no.ndla.common.configuration
 
+import sttp.client3.UriContext
+import sttp.model.Uri
+
 import scala.util.Properties.{propOrElse, propOrNone}
 
 trait BaseProps {
@@ -53,4 +56,9 @@ trait BaseProps {
   def SEARCH_INDEX_REPLICAS: Int = intPropOrDefault("SEARCH_INDEX_REPLICAS", 1)
 
   def TAPIR_THREADS: Int = intPropOrDefault("TAPIR_THREADS", 100)
+
+  def brightCoveAuthUri: String = s"https://oauth.brightcove.com/v4/access_token"
+  def brightCoveVideoUri(accountId: String, videoId: String): Uri =
+    uri"https://cms.api.brightcove.com/v1/accounts/$accountId/videos/$videoId/sources"
+
 }

From 46d4e79e8cd07babdfb2bb5a08562e75eab2ca1f Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Thu, 2 Jan 2025 11:30:15 +0100
Subject: [PATCH 25/31] Fix naming and test

---
 .../no/ndla/common/brightcove/NdlaBrightcoveClient.scala   | 7 +++----
 .../scala/no/ndla/common/configuration/BaseProps.scala     | 4 ++--
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
index 592848d19..0be52d591 100644
--- a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
+++ b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
@@ -21,14 +21,13 @@ trait NdlaBrightcoveClient {
   val brightcoveClient: NdlaBrightcoveClient
 
   class NdlaBrightcoveClient {
-    private val authUrl = props.brightCoveAuthUri
-    private val backend = HttpClientSyncBackend() // Or AsyncHttpClientFutureBackend()
+    private val backend = HttpClientSyncBackend()
 
     def getToken(clientID: String, clientSecret: String): Either[String, String] = {
       val request =
         basicRequest.auth
           .basic(clientID, clientSecret)
-          .post(uri"$authUrl?grant_type=client_credentials")
+          .post(uri"${props.BrightCoveAuthUri}?grant_type=client_credentials")
       val authResponse = request.send(backend)
 
       authResponse.body match {
@@ -43,7 +42,7 @@ trait NdlaBrightcoveClient {
 
     def getVideoSource(accountId: String, videoId: String, bearerToken: String): Either[String, Vector[Json]] = {
 
-      val videoSourceUrl = props.brightCoveVideoUri(accountId, videoId)
+      val videoSourceUrl = props.BrightCoveVideoUri(accountId, videoId)
       val request = basicRequest
         .header("Authorization", s"Bearer $bearerToken")
         .get(videoSourceUrl)
diff --git a/common/src/main/scala/no/ndla/common/configuration/BaseProps.scala b/common/src/main/scala/no/ndla/common/configuration/BaseProps.scala
index 6889bb36e..7ecd5f951 100644
--- a/common/src/main/scala/no/ndla/common/configuration/BaseProps.scala
+++ b/common/src/main/scala/no/ndla/common/configuration/BaseProps.scala
@@ -57,8 +57,8 @@ trait BaseProps {
 
   def TAPIR_THREADS: Int = intPropOrDefault("TAPIR_THREADS", 100)
 
-  def brightCoveAuthUri: String = s"https://oauth.brightcove.com/v4/access_token"
-  def brightCoveVideoUri(accountId: String, videoId: String): Uri =
+  def BrightCoveAuthUri: String = s"https://oauth.brightcove.com/v4/access_token"
+  def BrightCoveVideoUri(accountId: String, videoId: String): Uri =
     uri"https://cms.api.brightcove.com/v1/accounts/$accountId/videos/$videoId/sources"
 
 }

From a2a17f593cdfff574e7f5f72e9879b419aa2a7e7 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 6 Jan 2025 08:30:30 +0100
Subject: [PATCH 26/31] Fix naming of props

---
 .../src/main/scala/no/ndla/audioapi/AudioApiProperties.scala  | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala b/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
index 3430227d1..d6a9b6360 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/AudioApiProperties.scala
@@ -37,12 +37,12 @@ class AudioApiProperties extends BaseProps with DatabaseProps with StrictLogging
   val StorageName: String           = propOrElse("AUDIO_FILE_S3_BUCKET", s"$Environment.audio.ndla")
   val StorageRegion: Option[String] = propOrNone("AUDIO_FILE_S3_BUCKET_REGION")
 
-  val TranscribeStorageName: String = propOrElse("TRANSCRIBE_FILE_S3_BUCKET_NAME", s"$Environment.transcribe.ndla")
+  val TranscribeStorageName: String           = propOrElse("TRANSCRIBE_FILE_S3_BUCKET", s"$Environment.transcribe.ndla")
   val TranscribeStorageRegion: Option[String] = propOrNone("TRANSCRIBE_FILE_S3_BUCKET_REGION")
 
   val BrightcoveClientId: String     = prop("BRIGHTCOVE_API_CLIENT_ID")
   val BrightcoveClientSecret: String = prop("BRIGHTCOVE_API_CLIENT_SECRET")
-  val BrightcoveAccountId: String    = prop("NDLA_BRIGHTCOVE_ACCOUNT_ID")
+  val BrightcoveAccountId: String    = prop("BRIGHTCOVE_ACCOUNT_ID")
 
   val SearchServer: String                 = propOrElse("SEARCH_SERVER", "http://search-audio-api.ndla-local")
   val RunWithSignedSearchRequests: Boolean = propOrElse("RUN_WITH_SIGNED_SEARCH_REQUESTS", "true").toBoolean

From 0bd53391355b7bf8bc658467a725b61897462f22 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 6 Jan 2025 08:39:57 +0100
Subject: [PATCH 27/31] Fix error handling in api

---
 .../controller/TranscriptionController.scala       | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index d49beb040..ea270a70d 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -83,9 +83,7 @@ trait TranscriptionController {
       .serverLogicPure { _ =>
         { case (videoId, language, maxSpeakerOpt) =>
           transcriptionService.transcribeVideo(videoId, language, maxSpeakerOpt) match {
-            case Success(_) => Right(())
-            case Failure(ex: JobAlreadyFoundException) =>
-              returnLeftError(ex)
+            case Success(_)  => Right(())
             case Failure(ex) => returnLeftError(ex)
           }
         }
@@ -107,8 +105,7 @@ trait TranscriptionController {
               Right(TranscriptionResultDTO("COMPLETED", Some(transcriptionContent)))
             case Success(Left(jobStatus)) =>
               Right(TranscriptionResultDTO(jobStatus.toString, None))
-            case Failure(ex: NoSuchElementException) => returnLeftError(ex)
-            case Failure(ex)                         => returnLeftError(ex)
+            case Failure(ex) => returnLeftError(ex)
           }
         }
       }
@@ -127,9 +124,7 @@ trait TranscriptionController {
       .serverLogicPure { _ =>
         { case (audioName, audioId, language, maxSpeakerOpt, format) =>
           transcriptionService.transcribeAudio(audioName, audioId, language, maxSpeakerOpt, format) match {
-            case Success(_) => Right(())
-            case Failure(ex: JobAlreadyFoundException) =>
-              returnLeftError(ex)
+            case Success(_)  => Right(())
             case Failure(ex) => returnLeftError(ex)
           }
         }
@@ -151,8 +146,7 @@ trait TranscriptionController {
               Right(TranscriptionResultDTO("COMPLETED", Some(transcriptionContent)))
             case Success(Left(jobStatus)) =>
               Right(TranscriptionResultDTO(jobStatus.toString, None))
-            case Failure(ex: NoSuchElementException) => returnLeftError(ex)
-            case Failure(ex)                         => returnLeftError(ex)
+            case Failure(ex) => returnLeftError(ex)
           }
         }
       }

From 628be060f8fa2a5a0c83ff885dd917cdf75d356a Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 6 Jan 2025 12:01:14 +0100
Subject: [PATCH 28/31] Improve error handling

---
 .../service/TranscriptionService.scala        | 72 ++++++++++---------
 .../scala/no/ndla/audioapi/UnitSuite.scala    |  2 +-
 2 files changed, 41 insertions(+), 33 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index eb916823a..c727b0477 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -36,8 +36,6 @@ trait TranscriptionService {
         case Success(Left("IN_PROGRESS")) =>
           logger.info(s"Transcription already in progress for videoId: $videoId")
           return Failure(new JobAlreadyFoundException(s"Transcription already in progress for videoId: $videoId"))
-        case Success(Left(_)) =>
-          logger.info(s"Error occurred while checking transcription status for videoId")
         case _ =>
           logger.info(s"No existing transcription job for videoId: $videoId")
       }
@@ -93,7 +91,7 @@ trait TranscriptionService {
         if (transcriptionJobStatus == "COMPLETED") {
           val transcribeUri = s"transcription/$language/${videoId}.vtt"
 
-          getObjectFromS3(transcribeUri)
+          getObjectFromS3(transcribeUri).map(Right(_))
         } else {
           Success(Left(transcriptionJobStatus))
         }
@@ -114,8 +112,6 @@ trait TranscriptionService {
         case Success(Left("IN_PROGRESS")) =>
           logger.info(s"Transcription already in progress for videoId: $audioName")
           return Failure(new JobAlreadyFoundException(s"Transcription already in progress for audio: $audioName"))
-        case Success(Left(_)) =>
-          logger.info(s"Error occurred while checking transcription status for audio")
         case _ =>
           logger.info(s"No existing transcription job for audio name: $audioName")
       }
@@ -153,28 +149,32 @@ trait TranscriptionService {
         if (transcriptionJobStatus == "COMPLETED") {
           val transcribeUri = s"audio-transcription/$language/${audioId}"
 
-          getObjectFromS3(transcribeUri)
+          getObjectFromS3(transcribeUri).map(Right(_))
         } else {
           Success(Left(transcriptionJobStatus))
         }
       }
     }
 
-    private def getObjectFromS3(Uri: String): Try[Either[String, String]] = {
+    private def getObjectFromS3(Uri: String): Try[String] = {
       s3TranscribeClient.getObject(Uri).map { s3Object =>
         val content = scala.io.Source.fromInputStream(s3Object.stream).mkString
         s3Object.stream.close()
-        Right(content)
+        content
       }
     }
 
     def extractAudioFromVideo(videoId: String, language: String): Try[Unit] = {
       val accountId = props.BrightcoveAccountId
       val videoUrl = getVideo(accountId, videoId) match {
-        case Right(sources) => sources.head
-        case Left(error)    => throw new RuntimeException(s"Failed to get video sources: $error")
+        case Success(sources) if sources.nonEmpty => sources.head
+        case Success(_)  => return Failure(new RuntimeException(s"No video sources found for videoId: $videoId"))
+        case Failure(ex) => return Failure(new RuntimeException(s"Failed to get video sources: $ex"))
+      }
+      val videoFile = downloadVideo(videoId, videoUrl) match {
+        case Success(file) => file
+        case Failure(ex)   => throw new RuntimeException(s"Failed to download video: $ex")
       }
-      val videoFile = downloadVideo(videoId, videoUrl)
 
       val audioFile = new File(s"/tmp/audio_${videoId}.mp3")
 
@@ -223,37 +223,45 @@ trait TranscriptionService {
       }
     }
 
-    private def getVideo(accountId: String, videoId: String): Either[String, Vector[String]] = {
+    private def getVideo(accountId: String, videoId: String): Try[Vector[String]] = {
       val clientId     = props.BrightcoveClientId
       val clientSecret = props.BrightcoveClientSecret
-      val token        = brightcoveClient.getToken(clientId, clientSecret)
-      token match {
-        case Right(bearerToken) =>
-          val cake = brightcoveClient.getVideoSource(accountId, videoId, bearerToken)
-          cake match {
-            case Right(videoSources) =>
-              val mp4Sources = videoSources
-                .filter(source => source.hcursor.get[String]("container").toOption.contains("MP4"))
-                .map(source => source.hcursor.get[String]("src").toOption.getOrElse(""))
-              if (mp4Sources.nonEmpty) Right(mp4Sources)
-              else Left("No MP4 sources found for video.")
-            case Left(error) => Left(s"Failed to get video sources: $error")
-          }
-        case Left(error) =>
-          Left(s"Failed to retrieve bearer token: $error")
+
+      Try {
+        val token = brightcoveClient.getToken(clientId, clientSecret) match {
+          case Right(token) => token
+          case Left(error)  => throw new RuntimeException(s"Failed to retrieve bearer token: $error")
+        }
+
+        val videoSources = brightcoveClient.getVideoSource(accountId, videoId, token) match {
+          case Right(sources) => sources
+          case Left(error)    => throw new RuntimeException(s"Failed to get video sources: $error")
+        }
+
+        val mp4Sources = videoSources
+          .filter(source => source.hcursor.get[String]("container").toOption.contains("MP4"))
+          .map(source => source.hcursor.get[String]("src").toOption.getOrElse(""))
+
+        if (mp4Sources.isEmpty) mp4Sources
+        else throw new RuntimeException(s"No MP4 sources found for videoId: $videoId")
       }
     }
 
-    private def downloadVideo(videoId: String, videoUrl: String): File = {
+    private def downloadVideo(videoId: String, videoUrl: String): Try[File] = {
       val videoFile  = new File(s"/tmp/video_$videoId.mp4")
       val connection = HttpURLConnectionBackend()
 
       val response = basicRequest.get(uri"$videoUrl").response(asFile(videoFile)).send(connection)
-
-      response.body match {
-        case Right(file) => file
-        case Left(error) => throw new RuntimeException(s"Failed to download video: $error")
+      Try {
+        response.body match {
+          case Right(file) => file
+          case Left(error) => throw new RuntimeException(s"Failed to download video: $error")
+        }
+      } match {
+        case Success(file)      => Success(file)
+        case Failure(exception) => Failure(exception)
       }
+
     }
   }
 }
diff --git a/audio-api/src/test/scala/no/ndla/audioapi/UnitSuite.scala b/audio-api/src/test/scala/no/ndla/audioapi/UnitSuite.scala
index 76d6f9edf..7a8ddc91e 100644
--- a/audio-api/src/test/scala/no/ndla/audioapi/UnitSuite.scala
+++ b/audio-api/src/test/scala/no/ndla/audioapi/UnitSuite.scala
@@ -26,5 +26,5 @@ trait UnitSuite extends UnitTestSuite with PrivateMethodTester {
   setPropEnv("SEARCH_INDEX_NAME", "audio-integration-test-index")
   setPropEnv("BRIGHTCOVE_API_CLIENT_ID", "client-id")
   setPropEnv("BRIGHTCOVE_API_CLIENT_SECRET", "client")
-  setPropEnv("NDLA_BRIGHTCOVE_ACCOUNT_ID", "312532")
+  setPropEnv("BRIGHTCOVE_ACCOUNT_ID", "312532")
 }

From 6c355db04b29fe18397a16e03474ad6328589c3e Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 6 Jan 2025 12:19:03 +0100
Subject: [PATCH 29/31] Fix unused import and try handling of brightcove client

---
 .../controller/TranscriptionController.scala  |  2 +-
 .../brightcove/NdlaBrightcoveClient.scala     | 48 ++++++++++---------
 2 files changed, 27 insertions(+), 23 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
index ea270a70d..933ed1cf9 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/controller/TranscriptionController.scala
@@ -9,7 +9,7 @@
 package no.ndla.audioapi.controller
 
 import no.ndla.audioapi.Props
-import no.ndla.audioapi.model.api.{JobAlreadyFoundException, TranscriptionResultDTO}
+import no.ndla.audioapi.model.api.TranscriptionResultDTO
 import no.ndla.audioapi.service.{ReadService, TranscriptionService}
 import no.ndla.network.tapir.NoNullJsonPrinter.jsonBody
 import no.ndla.network.tapir.TapirController
diff --git a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
index 0be52d591..9a942ccd3 100644
--- a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
+++ b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
@@ -14,6 +14,8 @@ import io.circe.parser.*
 import sttp.client3.{HttpClientSyncBackend, UriContext, basicRequest}
 import no.ndla.common.configuration.HasBaseProps
 
+import scala.util.{Failure, Success, Try}
+
 case class TokenResponse(access_token: String, token_type: String, expires_in: Int)
 
 trait NdlaBrightcoveClient {
@@ -23,24 +25,25 @@ trait NdlaBrightcoveClient {
   class NdlaBrightcoveClient {
     private val backend = HttpClientSyncBackend()
 
-    def getToken(clientID: String, clientSecret: String): Either[String, String] = {
+    def getToken(clientID: String, clientSecret: String): Try[String] = {
       val request =
         basicRequest.auth
           .basic(clientID, clientSecret)
           .post(uri"${props.BrightCoveAuthUri}?grant_type=client_credentials")
       val authResponse = request.send(backend)
-
-      authResponse.body match {
-        case Right(jsonString) =>
-          decode[TokenResponse](jsonString) match {
-            case Right(tokenResponse) => Right(tokenResponse.access_token)
-            case Left(error)          => Left(s"Failed to decode token response: ${error.getMessage}")
-          }
-        case Left(error) => Left(s"Failed to get token: ${error}")
+      Try {
+        authResponse.body match {
+          case Right(jsonString) =>
+            decode[TokenResponse](jsonString) match {
+              case Right(tokenResponse) => tokenResponse.access_token
+              case Left(error)          => throw new Exception(s"Failed to decode token response: ${error.getMessage}")
+            }
+          case Left(error) => throw new Exception(s"Failed to get token: ${error}")
+        }
       }
     }
 
-    def getVideoSource(accountId: String, videoId: String, bearerToken: String): Either[String, Vector[Json]] = {
+    def getVideoSource(accountId: String, videoId: String, bearerToken: String): Try[Vector[Json]] = {
 
       val videoSourceUrl = props.BrightCoveVideoUri(accountId, videoId)
       val request = basicRequest
@@ -50,18 +53,19 @@ trait NdlaBrightcoveClient {
       implicit val backend = HttpClientSyncBackend()
 
       val response = request.send(backend)
-
-      response.body match {
-        case Right(jsonString) =>
-          parse(jsonString) match {
-            case Right(json) =>
-              json.asArray match {
-                case Some(videoSources) => Right(videoSources)
-                case None               => Left("Expected a JSON array but got something else.")
-              }
-            case Left(error) => Left(s"Failed to decode video source response: ${error.getMessage}")
-          }
-        case Left(error) => Left(s"Failed to get video source: ${error}")
+      Try {
+        response.body match {
+          case Right(jsonString) =>
+            parse(jsonString) match {
+              case Right(json) =>
+                json.asArray match {
+                  case Some(videoSources) => videoSources
+                  case None               => throw new Exception("Failed to parse video source")
+                }
+              case Left(error) => throw new Exception(s"Failed to parse video source: ${error.getMessage}")
+            }
+          case Left(error) => throw new Exception(s"Failed to get video source: ${error}")
+        }
       }
     }
   }

From ea32cc9630f13aaffd520f2d1265d5bdda76d173 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 6 Jan 2025 12:25:06 +0100
Subject: [PATCH 30/31] Remove unused import

---
 .../scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala  | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
index 9a942ccd3..7bfc26302 100644
--- a/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
+++ b/common/src/main/scala/no/ndla/common/brightcove/NdlaBrightcoveClient.scala
@@ -14,7 +14,7 @@ import io.circe.parser.*
 import sttp.client3.{HttpClientSyncBackend, UriContext, basicRequest}
 import no.ndla.common.configuration.HasBaseProps
 
-import scala.util.{Failure, Success, Try}
+import scala.util.Try
 
 case class TokenResponse(access_token: String, token_type: String, expires_in: Int)
 

From 574bc3793a170ca612b79ae3e7f87359012f13d5 Mon Sep 17 00:00:00 2001
From: ekrojo77 <even__kj@hotmail.com>
Date: Mon, 6 Jan 2025 12:32:55 +0100
Subject: [PATCH 31/31] update getVideo after brightcove changes

---
 .../service/TranscriptionService.scala        | 23 ++++++-------------
 1 file changed, 7 insertions(+), 16 deletions(-)

diff --git a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
index c727b0477..9169e8875 100644
--- a/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
+++ b/audio-api/src/main/scala/no/ndla/audioapi/service/TranscriptionService.scala
@@ -227,24 +227,15 @@ trait TranscriptionService {
       val clientId     = props.BrightcoveClientId
       val clientSecret = props.BrightcoveClientSecret
 
-      Try {
-        val token = brightcoveClient.getToken(clientId, clientSecret) match {
-          case Right(token) => token
-          case Left(error)  => throw new RuntimeException(s"Failed to retrieve bearer token: $error")
-        }
-
-        val videoSources = brightcoveClient.getVideoSource(accountId, videoId, token) match {
-          case Right(sources) => sources
-          case Left(error)    => throw new RuntimeException(s"Failed to get video sources: $error")
-        }
-
-        val mp4Sources = videoSources
+      for {
+        token   <- brightcoveClient.getToken(clientId, clientSecret)
+        sources <- brightcoveClient.getVideoSource(accountId, videoId, token)
+        mp4Sources = sources
           .filter(source => source.hcursor.get[String]("container").toOption.contains("MP4"))
           .map(source => source.hcursor.get[String]("src").toOption.getOrElse(""))
-
-        if (mp4Sources.isEmpty) mp4Sources
-        else throw new RuntimeException(s"No MP4 sources found for videoId: $videoId")
-      }
+        result <-
+          if (mp4Sources.nonEmpty) Success(mp4Sources) else Failure(new RuntimeException("No MP4 sources found"))
+      } yield result
     }
 
     private def downloadVideo(videoId: String, videoUrl: String): Try[File] = {