> ## 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.

# Connect ElevenLabs to the Context Router

> Configure an ElevenLabs Conversational AI agent to use SLNG's OpenAI-compatible Context Router as a custom LLM, with response caching.

ElevenLabs Conversational AI lets an agent use a **Custom LLM**: an OpenAI-compatible endpoint you supply instead of a built-in model. Point that at the SLNG [Context Router](/context-router) and your agent keeps its voice, prompt, and tools while gaining response caching.

**Prerequisites:**

* An [ElevenLabs](https://elevenlabs.io) account with a Conversational AI agent you can edit.
* An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys).
* Your region-specific router base URL from your SLNG contact (looks like `https://[region].context-router.slng.ai/v1`).

## Placeholders

| Placeholder                               | Replace with                                                          |
| ----------------------------------------- | --------------------------------------------------------------------- |
| `SLNG_API_KEY`                            | An SLNG key from [app.slng.ai/api-keys](https://app.slng.ai/api-keys) |
| `https://india.context-router.slng.ai/v1` | The exact region-specific base URL SLNG gave you                      |

## Dashboard setup

<Steps>
  <Step title="Open your agent's LLM settings">
    In the ElevenLabs dashboard, go to **Conversational AI**, open your agent, and find the **LLM** (or **Secondary LLM**) section of its configuration.

    <Frame caption="ElevenLabs agent LLM settings">
      {/* TODO: replace with screenshot of the agent LLM section */}

      <img src="https://mintcdn.com/slng/SmJQakEUJwFNsCYg/images/Screenshot-2026-07-28-at-09.22.22.png?fit=max&auto=format&n=SmJQakEUJwFNsCYg&q=85&s=0b2dca3d49cdabf38e8ca0c48f34b5bb" alt="Screenshot 2026 07 28 At 09 22 22" width="1078" height="1374" data-path="images/Screenshot-2026-07-28-at-09.22.22.png" />
    </Frame>
  </Step>

  <Step title="Choose Custom LLM">
    Select **Custom LLM** as the model provider. Set:

    * **Server URL / Base URL:** `https://india.context-router.slng.ai/v1`
    * **Model ID:** `slng/auto`
    * **API key:** `SLNG_API_KEY` (stored as a secret)

    ElevenLabs calls `<base-url>/chat/completions` with your key as a Bearer token, which is exactly what the router expects.

    <Frame caption="Custom LLM configuration">
      {/* TODO: replace with screenshot of the Custom LLM fields filled in */}

      <img src="https://mintcdn.com/slng/SmJQakEUJwFNsCYg/images/Screenshot-2026-07-28-at-09.23.42.png?fit=max&auto=format&n=SmJQakEUJwFNsCYg&q=85&s=fa1e0eb8f7fd64d22aa42d5be9d7e83f" alt="Screenshot 2026 07 28 At 09 23 42" width="1086" height="1318" data-path="images/Screenshot-2026-07-28-at-09.23.42.png" />
    </Frame>
  </Step>

  <Step title="Save and test the agent">
    Save the agent and start a test conversation. SLNG now answers every turn.
  </Step>
</Steps>

## Verify it is routing

Check the agent's conversation logs, or replay a turn directly with a cURL request.

## Related

<CardGroup cols={2}>
  <Card title="Context Router" icon="route" href="/llm-router">
    Endpoint, auth, request body, and response caching.
  </Card>

  <Card title="Voice platform integrations" icon="cable" href="/integrations/overview">
    Other ways to route your stack through SLNG.
  </Card>
</CardGroup>