Skip to content

Latest commit

 

History

History

voice

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
Dockerfile
Dockerfile
 
 
README.md
README.md
 
 
bot.py
bot.py
 
 
requirements.txt
requirements.txt
 
 

README.md

Voice Bot Starter

A voice-based conversational agent built with Pipecat.

Features

  • Real-time voice conversations powered by:
    • Deepgram (STT)
    • OpenAI (LLM)
    • Cartesia (TTS)
  • Voice activity detection with Silero
  • Support for interruptions

Required API Keys

  • OPENAI_API_KEY
  • DEEPGRAM_API_KEY
  • CARTESIA_API_KEY

Quick Customization

Change Bot Personality

Modify the system prompt in bot.py:

messages = [
    {
        "role": "system",
        "content": "You are Chatbot, a friendly, helpful robot..."
    },
]

Change Voice

Update the voice ID in the TTS service:

tts = CartesiaTTSService(
    api_key=os.getenv("CARTESIA_API_KEY"),
    voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22", # Change this
)

Deployment

See the top-level README for deployment instructions.