Overview
LiveKit Inference offers voice models powered by Inworld. Pricing information is available on the pricing page.
Model ID | Languages |
---|---|
inworld/inworld-tts-1 | enesfrkonlzhdeitjaplpt |
Usage
To use Inworld, pass a descriptor with the model and voice to the tts
argument in your AgentSession
:
from livekit.agents import AgentSessionsession = AgentSession(tts="inworld/inworld-tts-1:ashley",# ... llm, stt, vad, turn_detection, etc.)
import { AgentSession } from '@livekit/agents';session = new AgentSession({tts: "inworld/inworld-tts-1:ashley",// ... 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="inworld/inworld-tts-1",voice="ashley",language="en"),# ... tts, stt, vad, turn_detection, etc.)
import { AgentSession } from '@livekit/agents';session = new AgentSession({tts: new inference.TTS({model: "inworld/inworld-tts-1",voice: "ashley",language: "en"}),// ... tts, stt, vad, turn_detection, etc.});
The model ID from the models list.
Language code for the input text. If not set, the model default applies.
Additional parameters to pass to the Inworld TTS API. See the provider's documentation for more information.
Voices
LiveKit Inference supports all of the default voices available in the Inworld API. You can explore the available voices in the Inworld TTS Playground (free account required), and use the voice by copying its name into your LiveKit agent session.
Cloned voices are not yet supported in LiveKit Inference. To use these voices, create your own Inworld account and use the Inworld plugin for LiveKit Agents instead.
The following is a small sample of the Inworld voices available in LiveKit Inference.
Use the keyboard and arrows to audition voices
Use the keyboard and arrows to audition voices
Additional resources
The following links provide more information about Inworld in LiveKit Inference.