Skip to main content
Use LiveKit Agents for voice rooms and turn handling, with SomyaLabs Vyasa for speech recognition and Panini for speech synthesis.
SomyaLabs does not yet have a built-in LiveKit plugin or a LiveKit Inference model. Copy the SomyaLabs adapter into your agent project before using the short example below.

Install and configure

Use Python 3.10 or newer. Create a LiveKit Cloud project and a SomyaLabs API key, then install:
Save the adapter code as somya_livekit.py. Create .env.local in the same directory:
Keep this file on your agent server and out of source control and browser code. The SomyaLabs key authenticates speech requests; LiveKit uses its own project credentials for the room and the example LLM.

Create the agent

Save this as agent.py beside somya_livekit.py:
Run python agent.py dev, then open the agent in your LiveKit Cloud dashboard to speak to it. Change voice="arjun" to another voice slug if you prefer. Vyasa transcribes completed speech turns, so the agent does not receive interim transcripts. Panini streams audio chunks for playback as they arrive. See the adapter reference for how the HTTP requests and audio conversion work.