Skip to main content
Set websocket_url="wss://coda.api.rime.ai/ws" and model="coda" in rime.TTS to use Coda WebSocket v1. The plugin handles authorization, message encoding, sentence buffering, audio decoding, and connection reuse.

​
Install the plugin

Use Python 3.11 or later, uv, and livekit-plugins-rime version 1.8.2 or later. LiveKit Agents 1.8.2 introduced Coda WebSocket v1 support for both JSON and binary protocols, and earlier plugin versions do not accept websocket_url or websocket_protocol. Set RIME_API_KEY in your server’s environment, because the plugin sends this key to the selected endpoint. These commands create a project and install the LiveKit Rime plugin:
For an existing project, run the same uv add command in its directory to update the dependency requirement. The plugin installs compatible livekit-agents and rime-api dependencies. Commit your uv.lock file so deployments use the same dependencies.

​
Use the plugin in an agent session

Pass rime.TTS to your AgentSession. This example assumes that the agent already supplies speech recognition and an LLM. Set model="coda", because the plugin reads the model from a /{model}/ws path, and the path on coda.api.rime.ai is only /ws. Without model, the plugin raises ValueError.
Keep these points in mind:
  • Encoding: the plugin defaults to binary. Set websocket_protocol="json" to use JSON. Both modes support streaming through session.say() and streamed LLM replies, so do not add a tts.StreamAdapter.
  • Agent setup: for room setup, speech recognition, and an LLM, follow the LiveKit agent quickstart, then use the TTS configuration above.
  • Direct use: call stream() when you use the plugin directly, because the WebSocket provider’s synthesize() method raises an error. Call end_input() to finish input, then keep reading until synthesis ends. Both encodings produce decoded PCM frames.

​
Plugin parameters

These settings apply to both encodings: For 8 kHz mu-law, set both audio_format="audio/pcmu" and sample_rate=8000. The format alone leaves Coda at 24 kHz. The plugin decodes mu-law to 16-bit PCM at the selected rate.

​
Protocol limits

For splitStrategy, config.defaults, or codaParameters.textLookaheadTokens, use a direct client. The adapter does not expose these fields or provide aligned word timestamps.

​
Move from WS3 to v1

Use websocket_url and model for the endpoint, and time_scale_factor for speed. Remove these settings, because the v1 adapter rejects them:

​
Stream lifecycle

One LiveKit stream uses one Coda context. The adapter opens the context when the first non-empty sentence is ready and uses a pooled connection that has already received ready. The adapter also works in these ways:
  • Flush: call flush() only at a complete sentence or stable clause boundary. It can release incomplete buffered text, and there is no server-side flush operation. An input pause needs no message, and only end_input() finishes normal input.
  • Connections: sequential turns reuse pooled connections. Concurrent LiveKit streams use separate sockets.
  • Options: speech.update_options(...) changes settings for later streams. Active streams keep their initial settings.
  • Checks: the plugin checks the subprotocol, ready.protocol, context IDs, and event order. It discards connections after malformed responses or failed cancellation cleanup.
  • Timeouts: set connection and terminal timeouts with speech.stream(conn_options=...), using LiveKit’s APIConnectOptions.