> ## Documentation Index
> Fetch the complete documentation index at: https://docs.slng.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# LiveKit

> Add SLNG hosted speech to text and text to speech, and the SLNG Context Router, to a LiveKit agent.

Keep your LiveKit agent where it runs and swap its speech to text and text to
speech for SLNG hosted models. You can also point the language model at the SLNG
Context Router. The rest of your pipeline stays as it is.

There are two ways to do it. Set up the layers in the dashboard and copy the
migration prompt for your coding agent, or make the edits yourself.

## Prerequisites

* A running LiveKit agent (Python).
* An SLNG API key. See [Create your API key](/guides/get-started/quickstart#create-your-api-key).
* A BYOK LLM key registered in your org, so the router has a model to route to. See [Bring your own key](/guides/models/bring-your-own-key).
* For the assisted path, a coding agent that supports skills.

## Set up in the dashboard

Improving an agent is à la carte. Turn on speech to text, the language model,
text to speech, or any mix of the three, and leave the rest to your current
stack. You decide which layers to optimize. Set up the ones you want, then copy
the prompt SLNG builds from your choices.

<Steps>
  <Step title="Choose LiveKit">
    Start a new project, choose **Improve my agent**, and under **In your own
    code** select **LiveKit**.

    <Frame caption="Choose LiveKit in the Improve my agent flow.">
      <img src="https://mintcdn.com/slng-new-docs/_MURdOw87SJsfVag/heroshots/livekit-select.png?fit=max&auto=format&n=_MURdOw87SJsfVag&q=85&s=0d5e7a5a9204a823c18b11d942e8c1d3" alt="New project chooser with LiveKit highlighted under In your own code" width="2560" height="1600" data-path="heroshots/livekit-select.png" />
    </Frame>
  </Step>

  <Step title="Set up Listen">
    Open **Listen**, turn on speech to text, and choose the model your agent
    should use. Leave it off to keep your current speech to text.

    <Frame caption="Turn on Listen and pick a speech to text model.">
      <img src="https://mintcdn.com/slng-new-docs/_MURdOw87SJsfVag/heroshots/livekit-listen.png?fit=max&auto=format&n=_MURdOw87SJsfVag&q=85&s=f8167c298c81791a645ad7c59b24b9d1" alt="Listen section with the Include STT toggle on" width="2560" height="1600" data-path="heroshots/livekit-listen.png" />
    </Frame>
  </Step>

  <Step title="Set up Think">
    Open **Think**, turn on the language model, and choose the model your agent
    should use.

    <Frame caption="Think turned on with a language model selected.">
      <img src="https://mintcdn.com/slng-new-docs/_MURdOw87SJsfVag/heroshots/livekit-think.png?fit=max&auto=format&n=_MURdOw87SJsfVag&q=85&s=05db49582f832b19bf5f3c9f2956750c" alt="Think section with the language model turned on and a model chosen" width="2560" height="1600" data-path="heroshots/livekit-think.png" />
    </Frame>
  </Step>

  <Step title="Set up Speak">
    Open **Speak** and choose the text to speech model and voice. Use the
    **Include TTS** toggle to route this layer through SLNG or leave it on your
    current provider.

    <Frame caption="Use the Include TTS toggle to turn text to speech on or off.">
      <img src="https://mintcdn.com/slng-new-docs/_MURdOw87SJsfVag/heroshots/livekit-speak.png?fit=max&auto=format&n=_MURdOw87SJsfVag&q=85&s=8ca366f30fd71516baf012f884c9432a" alt="Speak section with the Include TTS toggle highlighted" width="2560" height="1600" data-path="heroshots/livekit-speak.png" />
    </Frame>
  </Step>

  <Step title="Copy the prompt">
    Click **Integrate** in the top right, then **Copy prompt** in the modal. The
    prompt is built from your Listen, Think, and Speak choices. Hand it to your
    coding agent, which installs the
    [`livekit-migration` skill](/guides/integrate/skills) and applies the change.

    <Columns cols={2}>
      <Frame caption="Click Integrate in the top right.">
        <img src="https://mintcdn.com/slng-new-docs/_MURdOw87SJsfVag/heroshots/livekit-integrate.png?fit=max&auto=format&n=_MURdOw87SJsfVag&q=85&s=38d4eebb62662fecd739dd9f668a9a15" alt="The Integrate button in the top right of the project" width="2560" height="1600" data-path="heroshots/livekit-integrate.png" />
      </Frame>

      <Frame caption="Copy the prompt.">
        <img src="https://mintcdn.com/slng-new-docs/_MURdOw87SJsfVag/heroshots/livekit-integrate-prompt.png?fit=max&auto=format&n=_MURdOw87SJsfVag&q=85&s=9d41a0d84735492232d483c987f6064e" alt="The Integrate modal with a Copy prompt button" width="2560" height="1600" data-path="heroshots/livekit-integrate-prompt.png" />
      </Frame>
    </Columns>

    <Accordion title="Example prompt">
      Your model IDs, voice, language, and region come from what you picked.

      ````md theme={null}
      # Migrate this LiveKit agent to SLNG hosted STT/TTS and the SLNG Context Router

      Use the SLNG `livekit-migration` skill to replace speech to text and
      text to speech with `slng.STT` and `slng.TTS`. Replace the LLM with
      LiveKit's OpenAI-compatible plugin pointed at the SLNG Context Router using
      `bedrock-mantle/nvidia.nemotron-nano-3-30b:latest`.

      ## Install the skill
      ```bash
      npx skills add slng-ai/skills livekit-migration
      ```

      ## Selected stack
      - STT: `slng/deepgram/nova:3-en`
      - TTS: `slng/fish/tts:s2.1-pro`
      - Voice: the voice you picked
      - Language: English (`en`)
      - Region: European Union, via the `eu.api.slng.ai` base URL
      - LLM: SLNG Context Router, model `bedrock-mantle/nvidia.nemotron-nano-3-30b:latest` at `https://au.context-router.slng.ai/v1`

      ## Instructions for the coding agent
      1. Discover the entrypoint, package manager, env loading, and current
         STT/TTS/LLM wiring before editing. Do not assume file names.
      2. Establish a rollback point with a clean git tree.
      3. Validate `SLNG_API_KEY` without printing it.
      4. Install `livekit-plugins-slng` and import-probe
         `from livekit.plugins import slng`.
      5. Replace the STT and TTS constructors with `slng.STT(...)` and
         `slng.TTS(...)`.
      6. Point the LLM at the SLNG Context Router endpoint.
      7. Never inline API keys. Verify one spoken turn that completes STT to
         LLM to TTS.
      ````
    </Accordion>
  </Step>
</Steps>

## Edit the code yourself

If you would rather not use a coding agent, make the same edits directly. The
removed lines below depend on your current providers, so match them to your
code.

<Steps>
  <Step title="Install the plugin">
    Use your project's package manager.

    ```bash theme={null}
    uv add livekit-plugins-slng
    ```
  </Step>

  <Step title="Point STT and TTS at SLNG">
    Swap the two constructors that feed your session. Keep the models, voice,
    language, and region you selected.

    ```diff theme={null}
    - from livekit.plugins import deepgram, cartesia
    + from livekit.plugins import slng

    - stt = deepgram.STT(model="nova-3")
    - tts = cartesia.TTS(voice="<your voice>")
    + stt = slng.STT(
    +     model="slng/deepgram/nova:3-en",
    +     language="en",
    +     base_url="eu.api.slng.ai",  # pin a region for latency or data residency; omit for api.slng.ai
    + )
    + tts = slng.TTS(
    +     model="slng/fish/tts:s2.1-pro",
    +     voice="<your voice>",  # the voice you picked in Speak, e.g. a Fish Audio voice
    +     language="en",
    +     base_url="eu.api.slng.ai",  # keep the same region as STT
    + )
    ```
  </Step>

  <Step title="Point the LLM at the SLNG Context Router">
    Keep LiveKit's OpenAI plugin and repoint it at the router. Pass stable agent
    and session identifiers in the headers. Use a fixed `agent_id` for the
    running agent and the current room or session ID for `session_id`.

    ```diff theme={null}
      from livekit.plugins import openai

    - llm = openai.LLM(model="gpt-4o")
    + llm = openai.LLM(
    +     base_url="https://au.context-router.slng.ai/v1",  # swap au for your region
    +     api_key=os.environ["SLNG_API_KEY"],
    +     model="bedrock-mantle/nvidia.nemotron-nano-3-30b:latest",
    +     extra_headers={
    +         "X-Slng-Agent-Id": agent_id,
    +         "X-Slng-Session-Id": session_id,
    +     },
    + )
    ```
  </Step>

  <Step title="Verify">
    Run one spoken turn through your agent and confirm it completes speech to
    text, the LLM, and text to speech.
  </Step>
</Steps>

## Next steps

* [Which models are available](/guides/models/which-models-are-available) for
  other speech models and voices you can route through SLNG.