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

# ElevenLabs

> Speech, transcription, sound effects and music. Voice-over for a demo, and transcripts of calls the site should answer.

Speech, transcription, sound effects and music. Voice-over for a demo, and transcripts of calls the site should answer.

## Connecting

In the dashboard, open **Connectors**, find ElevenLabs and press **Connect**. The key you enter is checked against ElevenLabs before anything is saved, so a key that is refused never becomes a connection that fails later.

### What you will need

| Field   | What it is                                 |
| ------- | ------------------------------------------ |
| API Key | Your ElevenLabs API key from the dashboard |

### Getting the credential

1. Go to [ElevenLabs](https://elevenlabs.io) and sign in
2. Navigate to **Profile Settings → API Keys**
3. Copy your API key (starts with `sk_`) and paste it into this connector

## Notes

* Free tier: 10,000 characters/month
* 3,000+ community voices available in the Voice Library
* See [ElevenLabs API docs](https://elevenlabs.io/docs/api-reference) for full reference

## What an agent can do with it

| Tool                    | What it does                                                                                                                             |
| ----------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| `convert`               | Convert text to speech using ElevenLabs. Returns audio binary in the requested format. Use list\_voices to discover available voice IDs. |
| `stream`                | Stream text-to-speech audio in real time. Same parameters as convert but returns streaming audio chunks. Ideal for low-latency playback. |
| `transcribe`            | Transcribe audio or video files to text using ElevenLabs Scribe. Supports 99 languages, speaker diarization, and word-level timestamps.  |
| `generate_sound_effect` | Generate sound effects from a text description. Returns audio binary. Duration can be specified or auto-detected from the prompt.        |
| `compose_music`         | Generate original music from a text description. Supports instrumental and vocal tracks up to 10 minutes.                                |
| `list_voices`           | List all available voices including pre-made voices and your cloned voices. Returns voice IDs, names, categories, and preview URLs.      |
| `get_voice`             | Get detailed information about a specific voice including settings and sample audio.                                                     |

## Useful resources

* [ElevenLabs documentation](https://elevenlabs.io/docs/api-reference)