GitDeployHub

langchain-ai/voice-demo

github.com/langchain-ai/voice-demo ↗
Python
10 environment variables found in .env.example

Set these on your host before deploying. Each platform has an “Environment Variables” section in the deploy flow.

  • LANGSMITH_API_KEY secret Shared
  • LANGSMITH_PROJECT_PREFIX
  • OPENAI_API_KEY secret Used by: both OpenAI Realtime backends (raw + Agents SDK), the LLM stage of the LiveKit and Pipecat cascades and their OpenAI Realtime…
  • DEEPGRAM_API_KEY secret Used by: the Pipecat cascade backend — Deepgram STT (Nova) + TTS (Aura).
  • ASSEMBLYAI_API_KEY secret Used by: the LiveKit cascade backend — AssemblyAI STT + Cartesia TTS.
  • CARTESIA_API_KEY secret
  • GOOGLE_API_KEY secret Used by: the Google ADK Live backend and the livekit-with-gemini-live variant.
  • LIVEKIT_API_KEY secret LiveKit — console mode doesn't need a real server, but the SDK still validates these at startup. Dummy values are fine.
  • LIVEKIT_API_SECRET secret
  • LIVEKIT_URL
Best match Fly.io Anything Dockerized — requires the Fly CLI.
macOS
brew install flyctl && fly launch --from https://github.com/langchain-ai/voice-demo
Linux
curl -L https://fly.io/install.sh | sh && fly launch --from https://github.com/langchain-ai/voice-demo
Windows (PowerShell)
iwr https://fly.io/install.ps1 -useb | iex; fly launch --from https://github.com/langchain-ai/voice-demo
Or deploy to a different host
← Try another repo