Skip to main content
The elevenlabs MCP adapter connects to the ElevenLabs API. List available voices and convert text to MP3 audio — ideal for podcast snippets, IVR prompts, accessibility outputs, and voice-enabled agent responses.

​
Prerequisites

  • An ElevenLabs account with an API key
  • Character quota sufficient for your synthesis volume
  • project_contributor access in AgentRuntime

​
Connect in AgentRuntime

1

Get an ElevenLabs API key

Sign in to ElevenLabs and copy your API key from profile settings.
2

Create a connection

Go to Connections and click New custom connection to create an API key connection with APIKey.
3

Add elevenlabs MCP instance

Go to MCP, click Add instance for elevenlabs, wire your connection on Instance config, set the profile active, and save.
4

Pick a voice

Run mcp_call → list_voices and note the voice_id for your default narrator.
See Authentication for binding connections to MCP instances.

​
What you can build

  • Daily audio brief — LLM summarizes RSS or news → text_to_speech → store MP3 in cloud storage.
  • Multilingual outreach — Translate text step → text_to_speech with eleven_multilingual_v2.
  • Workflow notifications — Short spoken alert for ops team when a human_task is assigned.
  • Content repurposing — Blog post → LLM abridgment → audio clip for social distribution.

​
Tools

ToolDescription
list_voicesList voices available to the API key
text_to_speechSynthesize speech from text; returns base64 MP3

​
Example

Convert an LLM summary to audio: 
{
  "id": "elevenlabs-tts",
  "type": "mcp_call",
  "name": "Synthesize briefing",
  "tool_name": "text_to_speech",
  "tool_args": {
    "voice_id": "{{input.voice_id}}",
    "text": "{{steps.llm-summary.result.text}}",
    "model_id": "eleven_multilingual_v2"
  },
  "depends_on": ["llm-summary"],
  "timeout_s": 60
}

​
Configuration

KeyRequiredDescription
APIKeyYesElevenLabs API key (xi-api-key header)
APIBaseNoElevenLabs API base URL

​
Troubleshooting

IssueFix
Voice not foundRun list_voices; voice IDs differ from display names
Quota exceededCheck character usage in ElevenLabs dashboard; shorten text or upgrade plan
Garbled or clipped audioSplit long text across multiple calls; respect model input limits
Wrong languageUse eleven_multilingual_v2 or a voice trained for the target language