Overview
LiveKit Inference offers voice models powered by Rime. Pricing information is available on the pricing page.
| Model ID | Languages |
|---|---|
| rime/arcana | enesfrde |
| rime/mistv2 | enesfrde |
Usage
The simplest way to use Rime TTS is to pass it to the tts argument in your AgentSession, including the model and voice to use:
from livekit.agents import AgentSessionsession = AgentSession(tts="rime/arcana:celeste",# ... llm, stt, vad, turn_detection, etc.)
import { AgentSession } from '@livekit/agents';session = new AgentSession({tts: "rime/arcana:celeste",// ... tts, stt, vad, turn_detection, etc.});
Parameters
To customize additional parameters, use the TTS class from the inference module:
from livekit.agents import AgentSession, inferencesession = AgentSession(tts=inference.TTS(model="rime/arcana",voice="celeste",language="en"),# ... tts, stt, vad, turn_detection, etc.)
import { AgentSession } from '@livekit/agents';session = new AgentSession({tts: new inference.TTS({model: "rime/arcana",voice: "celeste",language: "en"}),// ... tts, stt, vad, turn_detection, etc.});
stringRequiredThe model ID from the models list.
stringRequiredSee voices for guidance on selecting a voice.
stringOptionalTwo-letter language code for the input text. Note that the Rime API uses three-letter abbreviations (e.g. eng for English), but LiveKit Inference uses two-letter codes instead for consistency with other providers.
dictOptionalAdditional parameters to pass to the Rime TTS API. See the provider's documentation for more information.
In Node.js this parameter is called modelOptions.
Voices
LiveKit Inference supports all of the voices available in the Rime API. You can view the default voices and explore the wider set in the API in the Rime voices documentation, and use the voice by copying its name into your LiveKit agent session.
The following is a small sample of the Rime voices available in LiveKit Inference.
Additional resources
The following links provide more information about Rime in LiveKit Inference.