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

# ElevenLabs integration guide

This tutorial walks you through building low-latency Conversational AI agents using ElevenLabs and SambaCloud’s high-speed LLM inference engine. Low latency is crucial for smooth voice conversations, and SambaNova delivers this with specialized hardware optimized for world-class inference speeds using open-source models.

## Prerequisites

Before starting, ensure you have:

* Free account on [SambaCloud](http://cloud.sambanova.ai?utm_source=elevenlabs\&utm_medium=external\&utm_campaign=cloud_signup).
* Free account on [Eleven Labs](https://elevenlabs.io/app/sign-in).

## Setup

Follow these steps to set up your AI agent.

### Access the agent in ElevenLabs

1. Go to the [Agents page on ElevenLabs](https://elevenlabs.io/app/sign-in?redirect=%2Fapp%2Fconversational-ai%2Fagents).
2. Create a new agent, or select an existing agent to edit.

<img src="https://mintcdn.com/sambanova-systems/tKEjjixpklKce6C2/images/docs/integrations/elevenlabs/elevenlabs1.png?fit=max&auto=format&n=tKEjjixpklKce6C2&q=85&s=7ca6fb8e29161bb6bf6015de5230fd0d" alt="ElevenLabs Agents page" width="1920" height="583" data-path="images/docs/integrations/elevenlabs/elevenlabs1.png" />

### Configure the LLM settings

1. Scroll to the LLM section of your agent settings.
2. Select Custom LLM from the dropdown menu.

<img src="https://mintcdn.com/sambanova-systems/tKEjjixpklKce6C2/images/docs/integrations/elevenlabs/elevenlabs2.png?fit=max&auto=format&n=tKEjjixpklKce6C2&q=85&s=b015369f60e66b4a99dcff304b175126" alt="ElevenLabs LLM settings with Custom LLM selected" width="1920" height="911" data-path="images/docs/integrations/elevenlabs/elevenlabs2.png" />

### Retrieve SambaNova endpoint and model

1. Open the [SambaCloud Playground](https://cloud.sambanova.ai/playground).
2. Select View Code in the top-right to get your model endpoint URL and model name.

<img src="https://mintcdn.com/sambanova-systems/tKEjjixpklKce6C2/images/docs/integrations/elevenlabs/elevenlabs3.png?fit=max&auto=format&n=tKEjjixpklKce6C2&q=85&s=7f7729b3156d2c30cf9d327f252a6fb6" alt="SambaCloud Playground View Code panel" width="1920" height="1144" data-path="images/docs/integrations/elevenlabs/elevenlabs3.png" />

### Generate your SambaNova API key

1. Go to your SambaCloud account.
2. Generate an API key from the portal.

<img src="https://mintcdn.com/sambanova-systems/tKEjjixpklKce6C2/images/docs/integrations/elevenlabs/elevenlabs5.png?fit=max&auto=format&n=tKEjjixpklKce6C2&q=85&s=b8f6bac3e8e09eda2ff87b7bf816d103" alt="SambaCloud API key generation page" width="1920" height="1136" data-path="images/docs/integrations/elevenlabs/elevenlabs5.png" />

### Add API key to ElevenLabs

1. Return to the ElevenLabs agent settings page.
2. Under Workspace Secrets, add name and value.
3. Name: SAMBANOVA\_API\_KEY.
4. Value: Paste the API key from previous step.

<img src="https://mintcdn.com/sambanova-systems/tKEjjixpklKce6C2/images/docs/integrations/elevenlabs/elevenlabs6.png?fit=max&auto=format&n=tKEjjixpklKce6C2&q=85&s=b9f441460f734321172251cf2e77dbfa" alt="ElevenLabs Workspace Secrets with SAMBANOVA_API_KEY added" width="1920" height="971" data-path="images/docs/integrations/elevenlabs/elevenlabs6.png" />

<Note>
  This enables ElevenLabs to access your SambaNova model.
</Note>

### Set token limit

In the Limit token usage section, set maximum tokens to `1024`. This helps control the response length for optimal conversational flow.

### Save and test

1. Select Save to apply changes.
2. Test your setup by selecting Test AI agent followed by Call AI agent.
3. See video walkthrough for details.

## Video walkthrough

<iframe width="560" height="315" src="https://www.youtube.com/embed/46W96JcE_p8?cc_load_policy=1" title="Tutorial: Building conversational AI agents with ElevenLabs and SambaNova" frameBorder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerPolicy="strict-origin-when-cross-origin" allowFullScreen />
