ElevenLabs
Generate realistic AI speech from text. Over 100 voices in 29 languages. Create audio for websites, podcasts, and video narration.
🔑 Setup Required — Bring Your Own Key
This integration requires API credentials. Store them once via
setup_integration or the Dashboard Vault — they're encrypted
with AES-256-GCM and never exposed.
Required Credentials
elevenlabs_api_key
API Key
API key from elevenlabs.io → Profile → API Key.
Get your API key at elevenlabs.io →
Endpoints (3)
POST
text-to-speech
Convert text to speech. Returns audio data. Use voice IDs from list-voices. Default voice: Rachel (21m00Tcm4TlvDq8ikWAM).
| Field | Type | Required | Description |
|---|---|---|---|
voice_id |
string | ✓ Yes | Voice ID from list-voices. Popular: "21m00Tcm4TlvDq8ikWAM" (Rachel), "EXAVITQu4vr4xnSDxMaL" (Bella). |
text |
string | ✓ Yes | Text to convert to speech (max 5000 chars). |
model_id |
string | No | Model to use. Default: "eleven_monolingual_v1". Multilingual: "eleven_multilingual_v2". |
GET
list-voices
List all available voices. Returns voice ID, name, category, language, and preview URL.
No input parameters required.
GET
get-voice
Get details for a specific voice: name, description, samples, language, and settings.
| Field | Type | Required | Description |
|---|---|---|---|
voice_id |
string | ✓ Yes | Voice ID to get details for. |
MCP Tool Names
When using this integration through an AI assistant (Claude, ChatGPT, Cursor, etc.), the endpoints are available as MCP tools:
| Endpoint | MCP Tool Name |
|---|---|
| text-to-speech | elevenlabs_text_to_speech |
| list-voices | elevenlabs_list_voices |
| get-voice | elevenlabs_get_voice |