ElevenLabs MCP
by ElevenLabs
Text-to-speech, voice cloning, and audio processing for AI assistants
ai-ml Python Beginner Self-hostable Verified
⭐ 1.2k stars 📅 Updated: 1mo ago
Description
Official ElevenLabs MCP server providing text-to-speech, voice cloning, audio transcription, voice design, and audio isolation capabilities. Converts text to natural-sounding speech using ElevenLabs' industry-leading voice synthesis models. Supports configurable output modes — save audio as files, return as MCP resources, or both. Includes enterprise data residency support for compliance-sensitive deployments. Install via uvx or pip for immediate access to the full ElevenLabs audio toolkit from any MCP client.
✅ Best for
Any AI workflow that needs high-quality speech synthesis, voice cloning, or audio processing
⏭️ Skip if
You only need basic TTS and prefer a free, local solution
💡 Use cases
- Generating natural-sounding speech from text within AI assistant workflows
- Cloning voices for personalized audio content creation
- Transcribing audio files to text with high accuracy
- Isolating vocals from background noise in audio recordings
👍 Pros
- ✓ Industry-leading voice quality powered by ElevenLabs synthesis models
- ✓ Official first-party server with full API coverage
- ✓ Flexible output modes — files, resources, or both
- ✓ Enterprise data residency support for compliance requirements
👎 Cons
- ✗ Requires paid ElevenLabs API key for meaningful usage beyond free tier
- ✗ Audio generation can be slow for long text passages
- ✗ Voice cloning requires sample audio of sufficient quality and length
🔧 Exposed tools (5 tools)
| Tool | Category | Description |
|---|---|---|
| isolate_audio | processing | Isolate vocals from background noise in audio recordings |
| text_to_speech | synthesis | Convert text to natural-sounding speech audio |
| transcribe_audio | transcription | Transcribe audio files to text |
| clone_voice | voice | Clone a voice from audio samples for custom speech generation |
| design_voice | voice | Design a new synthetic voice with configurable parameters |
⚡ Installation
Prerequisites:
- • python v3.10+
- • ElevenLabs API key
- • API key required
Check Claude Code documentation to configure this MCP server.
💡 Tips & tricks
Use uvx elevenlabs-mcp for the simplest install. Configure the output directory via environment variables to control where generated audio files are saved. Voice cloning works best with 1-3 minutes of clean speech audio.
Quick info
- Author
- ElevenLabs
- License
- MIT
- Runtime
- Python 3.10+
- Transport
- stdio
- Category
- ai-ml
- Difficulty
- Beginner
- Self-hostable
- ✅
- Auth
- —
- Docker
- —
- Version
- latest
- Updated
- Feb 28, 2026
Client compatibility
- ✅ Claude Code
- ✅ Cursor
- ❓ VS Code Copilot
- ❓ Gemini CLI
- ✅ Windsurf
- ❓ Cline
- ❓ JetBrains AI
- ❓ Warp
Platforms
🍎 macOS 🐧 Linux 🪟 Windows