Converse

Developer documentation

Build a realtime voice experience

Converse handles speech recognition, turn-taking, response generation, speech synthesis and interruption detection. Start with the browser SDK when you want us to handle the microphone, echo cancellation and playback too.

Get an API key Browser quickstart

Choose your path

Recommended
Browser SDKWeb apps with microphone capture, echo cancellation and playback included.
Headless
Python SDKServices and devices that already manage audio capture and playback.
Telephony
TwilioInbound phone calls through a maintained Media Streams bridge.
Protocol
WebSocket APIOther languages and custom media stacks with direct protocol control.

Browser quickstart

Four steps to your first conversation

  1. Install the SDK. Run npm install @trelis/converse. View it on npm.
  2. Create a persistent key. Keep it on your backend; never ship it in browser JavaScript.
  3. Mint a scoped session credential. Your authenticated backend calls POST /api/v1/session-keys with the persistent key.
  4. Connect the browser SDK. Pass the scoped credential to ConverseClient, then unlock audio, connect and start the microphone from a user gesture.

Open the browser guide →

Exact references

When you need protocol details

HTTP APISession credentials, available voices and response schemas. Realtime protocolWebSocket operations, events and message formats.

npm · PyPI · OpenAPI JSON · AsyncAPI JSON