Minh/s2s context summary (#1813)

Author: minh-hoque

.gitignore

@@ -144,3 +144,4 @@ examples/fine-tuned_qa/local_cache/*
 
 # VS Code files
 .vscode/
+.cursorignore

examples/Context_summarization_with_realtime_api.ipynb

@@ -142,7 +142,7 @@
     "### How it works\n",
     "\n",
     "\n",
-    "![STT Not Streaming Transcription flow](./imgs/speech-to-text-not-streaming.png)\n",
+    "![STT Not Streaming Transcription flow](../images/speech-to-text-not-streaming.png)\n",
     "\n",
     "#### Benefits\n",
     "\n",
@@ -250,7 +250,7 @@
     "- You need immediate transcription results (partial or final) as they arrive.  \n",
     "- Scenarios where partial feedback improves UX, e.g., uploading a long voice memo.\n",
     "\n",
-    "![STT Streaming Transcription flow](./imgs/speech-to-text-streaming.png)\n",
+    "![STT Streaming Transcription flow](../images/speech-to-text-streaming.png)\n",
     "\n",
     "#### Benefits\n",
     "- **Real-time feel:** Users see transcription updates almost immediately.  \n",
@@ -321,7 +321,7 @@
    "source": [
     "### How it works\n",
     "\n",
-    "![Realtime Transcription flow](./imgs/realtime_api_transcription.png)\n",
+    "![Realtime Transcription flow](../images/realtime_api_transcription.png)\n",
     "\n",
     "#### Benefits\n",
     "- **Ultra-low latency:** Typically 300–800 ms, enabling near-instant transcription.  \n",
@@ -496,7 +496,7 @@
    "source": [
     "### How it works\n",
     "\n",
-    "![Agents Transcription flow](./imgs/agents_sdk_transcription.png)\n",
+    "![Agents Transcription flow](../images/agents_sdk_transcription.png)\n",
     "\n",
     "**Benefits**\n",
     "\n",

examples/Speech_transcription_methods.ipynb

@@ -4,6 +4,16 @@
 # should build pages for, and indicates metadata such as tags, creation date and
 # authors for each page.
 
+- title: Context Summarization with Realtime API
+  path: examples/Context_summarization_with_realtime_api.ipynb
+  date: 2025-05-10
+  authors:
+    - minh-hoque
+  tags:
+    - audio
+    - speech
+    - tiktoken
+
 - title: Comparing Speech-to-Text Methods with the OpenAI API
   path: examples/Speech_transcription_methods.ipynb
   date: 2025-04-29