Overview
LiveKit Inference offers transcription powered by Cartesia. Pricing information is available on the pricing page.
Model name | Model ID | Languages |
---|---|---|
Ink Whisper | cartesia/ink-whisper | enzhdeesrukofrjapttrplcanlarsvitidviheukelmscsrodahutanothurhrbgltlamimlcysktefalvbnsrazslknetmkbreuishynemnbskksqswglmrpasikmsnyosoafockabetgsdguamyilouzfohtpstknnmtsalbmybotlmgastthawlnhabajwsuyue |
Usage
To use Cartesia, pass a descriptor with the model and language to the stt
argument in your AgentSession
:
from livekit.agents import AgentSessionsession = AgentSession(stt="cartesia/ink-whisper:en",# ... tts, stt, vad, turn_detection, etc.)
import { AgentSession } from '@livekit/agents';session = new AgentSession({stt: "cartesia/ink-whisper:en",// ... tts, stt, vad, turn_detection, etc.});
Parameters
To customize additional parameters, use the STT
class from the inference
module:
from livekit.agents import AgentSession, inferencesession = AgentSession(stt=inference.STT(model="cartesia/ink-whisper",language="en"),# ... tts, stt, vad, turn_detection, etc.)
import { AgentSession, inference } from '@livekit/agents';session = new AgentSession({stt: new inference.STT({model: "cartesia/ink-whisper",language: "en"}),// ... tts, stt, vad, turn_detection, etc.});
The model to use for the STT.
Language code for the transcription. If not set, the provider default applies.
Additional parameters to pass to the Cartesia STT API, including min_volume
, and max_silence_duration_secs
. See the provider's documentation for more information.
Additional resources
The following links provide more information about Cartesia in LiveKit Inference.