Cartesia STT plugin guide

Available in

Python

Overview

This plugin allows you to use Cartesia as an STT provider for your voice agents.

LiveKit Inference

Cartesia STT is also available in LiveKit Inference, with billing and integration handled automatically. See the docs for more information.

This section includes a basic usage example and some reference material. For links to more detailed documentation, see Additional resources.

Install the plugin from PyPI:

uv add "livekit-agents[cartesia]~=1.2"

The Cartesia plugin requires a Cartesia API key.

Set CARTESIA_API_KEY in your .env file.

Use Cartesia STT in an AgentSession or as a standalone transcription service. For example, you can use this STT in the Voice AI quickstart.

from livekit.plugins import cartesia

session = AgentSession(
   stt = cartesia.STT(
      model="ink-whisper"
   ),
   # ... llm, tts, etc.
)

This section describes some of the available parameters. See the plugin reference for a complete list of all available parameters.

modelstringOptionalDefault: ink-whisper

Selected model to use for STT. See Cartesia STT models for supported values.

languagestringOptionalDefault: en

Language of input audio in ISO-639-1 format. See Cartesia STT models for supported values.

The following resources provide more information about using Cartesia with LiveKit Agents.

The livekit-plugins-cartesia package on PyPI.

Reference for the Cartesia STT plugin.

View the source or contribute to the LiveKit Cartesia STT plugin.

Cartesia STT docs.

Get started with LiveKit Agents and Cartesia STT.

Guide to the Cartesia TTS plugin with LiveKit Agents.