# ElevenLabs MCP

> Official ElevenLabs server: TTS, voice cloning, SFX, music, and dialogue isolation.

- **Category:** Voice & Dialogue
- **Vendor:** ElevenLabs (official)
- **Pricing:** freemium
- **Verified:** 2026-06-11

## What it does

The official ElevenLabs MCP server exposes the full audio platform: text-to-speech with thousands of voices, voice cloning and design, text-to-sound-effects, Eleven Music composition, transcription, and audio isolation. For a filmmaker-agent it covers dialogue, SFX, and score from a single API key — the most complete one-stop audio MCP for a film pipeline.

## Connect

- Claude Code: `claude mcp add elevenlabs -e ELEVENLABS_API_KEY=YOUR_KEY -- uvx elevenlabs-mcp`
- Local: `uvx elevenlabs-mcp`

**Auth:** api_key (env `ELEVENLABS_API_KEY`) — ElevenLabs dashboard at elevenlabs.io (free tier: 10k credits/month)

## Capabilities

`tts` · `voice-cloning` · `voice-design` · `sfx` · `music` · `transcription` · `audio-isolation` · `speech-to-speech`

## Sample tools

`text_to_speech` · `speech_to_text` · `text_to_sound_effects` · `voice_clone` · `text_to_voice` · `isolate_audio` · `compose_music` · `create_composition_plan` · `search_voice_library` · `play_audio`

## Field notes

Actively maintained (v0.9.1, Jan 2026, ~1.4k stars); also published as Docker image mcp/elevenlabs and on PyPI. Optional env: ELEVENLABS_MCP_BASE_PATH, ELEVENLABS_MCP_OUTPUT_MODE, ELEVENLABS_API_RESIDENCY. Local stdio only — no hosted remote MCP as of June 2026.

## Links

- Site: https://elevenlabs.io
- Docs: https://elevenlabs.io/blog/introducing-elevenlabs-mcp
- Repo: https://github.com/elevenlabs/elevenlabs-mcp

---

Structured data: https://mcp.film/api/mcps/elevenlabs.json · Directory: https://mcp.film