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

# Cerebrium

> Deploy Rime TTS on Cerebrium's serverless infrastructure.

export const IntegrationHeader = ({partnerLogo, partnerAlt = "Partner logo", rimeLogo = "/images/rime_logo_new.svg", rimeAlt = "Rime logo", rimeHeight = "40px", partnerHeight = "40px"}) => <div style={{
  width: "100%",
  display: "flex",
  flexDirection: "row",
  alignItems: "center",
  justifyContent: "center",
  gap: "12px",
  flexWrap: "nowrap",
  marginBottom: "24px"
}}>
    <img src={rimeLogo} style={{
  height: rimeHeight,
  display: "inline-block"
}} alt={rimeAlt} />
    <span style={{
  fontSize: "24px",
  color: "#666",
  display: "inline-block"
}}>
      +
    </span>
    <img src={partnerLogo} style={{
  height: partnerHeight,
  display: "inline-block"
}} alt={partnerAlt} />
  </div>;

<IntegrationHeader partnerLogo="/images/cerebrium.png" partnerAlt="Cerebrium logo" />

[Cerebrium](https://www.cerebrium.ai/) is a serverless infrastructure platform purpose-built for building and scaling AI applications with minimal infrastructure overhead. With ultra-low time-to-first-byte (TTFB) performance, enterprise-grade compliance, and support for global deployments, Cerebrium makes it easy to take applications from prototype to production in minutes.

Rime’s text-to-speech (TTS) synthesis model is now available through Cerebrium. With Cerebrium’s Rime integration, you can develop responsive AI voice applications that deliver natural, lifelike interactions.

### Get started

Developers can now deploy Rime’s text-to-speech services on Cerebrium:

1. Create a Rime account and obtain your API key.
2. Create a secret in Cerebrium named `RIME_API_KEY` with your Rime key.
3. Initialize your app with the Cerebrium CLI (v1.39.0 or higher):

```bash theme={null}
cerebrium init rime
```

4. Define your deployment using a `cerebrium.toml` file with the `[cerebrium.runtime.rime]` configuration. Specify your compute resources (e.g., AMPERE\_A10 GPU, memory, CPU), scaling parameters, and region (e.g., `us-east-1`).
   See [Cerebrium's documentation](https://docs.cerebrium.ai/cerebrium/partner-services/rime#rime) for full implementation details.

5. Deploy with:

```bash theme={null}
cerebrium deploy
```

Once deployed, you can send real-time TTS inference requests using either:

* REST API, with an endpoint like:

```bash theme={null}
https://api.cortex.cerebrium.ai/v4/<project-id>/rime
```

Include your RIME API key in the Authorization header and specify your desired speaker, model, and text.

* WebSocket interface for streaming audio

Rime handles API authentication via the key you provide, and your containers will scale automatically based on the concurrency and replica settings defined in the TOML file.

For full setup instructions, see the [Cerebrium documentation](https://docs.cerebrium.ai/cerebrium/partner-services/rime#rime).