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

# Resemble AI

> Use the Resemble AI text-to-speech plugin in a Zero Runtime pipeline.

Resemble AI is a **text-to-speech** plugin. It turns the LLM's reply into audio the
caller hears, using Resemble AI's custom neural voice clones.

## Setup

Set your Resemble AI API key in the worker environment. Generate a key from the [Resemble AI dashboard](https://app.resemble.ai/account/api):

```bash theme={null}
export RESEMBLE_API_KEY=<key>
```

## Usage

Import the plugin and pass it to the pipeline's `tts` slot.

<CodeGroup>
  ```python Python theme={null}
  from zeroruntime.plugins import ResembleTTS

  tts = ResembleTTS()

  # Pipeline(tts=tts, ...)
  ```

  ```typescript Node JS theme={null}
  import { ResembleTTS } from '@zeroruntime/js-sdk/plugins';

  const tts = ResembleTTS();

  // Pipeline({ tts, ... })
  ```
</CodeGroup>

## Parameters

| Parameter | Type | Default | Description |
| - | - | - | - |
| `api_key` | `str \| None` | `None` | Resemble AI API key. Falls back to the `RESEMBLE_API_KEY` environment variable when unset. |
| `voice_uuid` | `str` | `"55592656"` | UUID of the Resemble AI voice (custom or pre-built) to use for synthesis. Retrieve voice UUIDs from the Resemble AI dashboard or the `/voices` API endpoint. |
| `sample_rate` | `int` | `22050` | Output audio sample rate in Hz. |

Spoken replies support interruptions. When the caller talks over the agent, the runtime
stops the audio and listens again. See the [plugins overview](/runtime-sdk/plugins/overview) for how TTS fits into the rest of the pipeline.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.