LiveKit Inference

Overview

LiveKit Inference provides access to many of the best models and providers for voice agents, including models from OpenAI, Google, AssemblyAI, Deepgram, Cartesia, ElevenLabs, and more. LiveKit Inference is included in LiveKit Cloud, and does not require any additional plugins. It's zero data retention by default, so your prompts, audio, and model outputs are never stored or used to train models. See the guides for LLM, STT, and TTS for supported models and configuration options.

To learn more about LiveKit Inference, see the blog post Introducing LiveKit Inference: A unified model interface for voice AI .

For LiveKit Inference models, use the inference module classes in your AgentSession:

from livekit.agents import AgentSession, inference

session = AgentSession(
    stt=inference.STT(
        model="deepgram/flux-general",
        language="en"
    ),
    llm=inference.LLM(
        model="google/gemma-4-31b-it",
    ),
    tts=inference.TTS(
        model="cartesia/sonic-3",
        voice="9626c31c-bec5-4cca-baa8-f8ba9e84c8bc",
    ),
)

import { AgentSession, inference } from '@livekit/agents';

session = new AgentSession({
    stt: new inference.STT({
        model: "deepgram/flux-general",
        language: "en"
    }),
    llm: new inference.LLM({
        model: "google/gemma-4-31b-it",
    }),
    tts: new inference.TTS({
        model: "cartesia/sonic-3",
        voice: "9626c31c-bec5-4cca-baa8-f8ba9e84c8bc",
    }),
});

String descriptors

As a shortcut, you can pass a model descriptor string directly instead of using the inference classes. This is a convenient way to get started quickly.

from livekit.agents import AgentSession

session = AgentSession(
    stt="deepgram/nova-3:en",
    llm="google/gemma-4-31b-it",
    tts="cartesia/sonic-3:9626c31c-bec5-4cca-baa8-f8ba9e84c8bc",
)

import { AgentSession } from '@livekit/agents';

session = new AgentSession({
    stt: "deepgram/nova-3:en",
    llm: "google/gemma-4-31b-it",
    tts: "cartesia/sonic-3:9626c31c-bec5-4cca-baa8-f8ba9e84c8bc",
});

For detailed parameter references and model-specific options, see the individual model guides for LLM, STT, and TTS.

Zero data retention

LiveKit Inference is zero data retention (ZDR) by default. Your prompts, audio, and model outputs pass through only to generate a response. Neither LiveKit nor the underlying model providers log, store, or train on your data. This applies to every LLM, STT, and TTS model, on every plan, with no configuration required.

Models

The following tables list all models currently available through LiveKit Inference.

Large language models (LLM)

Speech-to-text (STT)

Text-to-speech (TTS)

Billing

LiveKit Inference billing is based on usage. Discounted rates are available on the Scale plan. Custom rates are available on the Enterprise plan. Refer to the following articles for more information on quotas, limits, and billing for LiveKit Inference. The latest pricing is always available on the LiveKit Inference pricing page .