LiveKit Community

Thanks for reaching out, Oliver. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.


The Cartesia TTS integration with LiveKit enables customizable speech synthesis with natural-sounding speech and low latency, ideal for building voice AI applications.

*Key Features:*
• Customizable parameters like *model*, *voice*, *language*, *speed*, and *emotion*.
• Support for *SSML customization* to fine-tune pronunciation.
• Options for *streaming synthesis* and *word timestamps*.
*Setup:*
1. Install the Cartesia plugin using:
```pip install "livekit-agents[cartesia]~=1.0"```
1. Set your Cartesia API key as the `CARTESIA_API_KEY` environment variable.
*Basic Usage:*
```from livekit.plugins import cartesia

session = AgentSession(
    tts=cartesia.TTS(
        model="sonic-2",
        voice="f786b574-daa5-4673-aa0c-cbe3e8534c02",
    )
    # ... llm, stt, etc.
)```
If you need further details or assistance with specific configurations, let me know!
 Sources: <https://github.com/livekit/agents-js/blob/20f5ef49fe9051419af3c3f502253d4a093bbbbf/plugins/cartesia/src/tts.ts#L1-L81|plugins/cartesia/src/tts.ts> | <https://docs.livekit.io/agents/integrations/tts/cartesia/|Cartesia TTS integration guide | LiveKit Docs> | <https://github.com/livekit/agents/blob/9c76e2e67f9817dc63b5db07540bec3ef1b55ae1/examples/other/text-to-speech/cartesia_tts.py#L1-L59|examples/other/text-to-speech/cartesia_tts.py>