MCP Coqui TTS Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Coqui TTS Server say 'Hello, world!' and save to hello.wav"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Coqui TTS Server
A Model Context Protocol (MCP) server that provides text-to-speech synthesis capabilities using Coqui TTS, including voice cloning support.
Features
Text-to-Speech Synthesis: Convert text to natural-sounding speech
Multiple Models: Support for various TTS models and languages
Voice Cloning: Clone voices from audio samples using XTTS models
Long Text Support: Automatic chunking for longer texts
Customizable Output: Control speed, speaker, and language settings
Related MCP server: MCP MeloTTS Audio Generator
Prerequisites
Before using this MCP server, you need to install Coqui TTS:
pip install TTSFor voice cloning and concatenation features, you'll also need ffmpeg:
# macOS
brew install ffmpeg
# Ubuntu/Debian
sudo apt-get install ffmpeg
# Windows (using chocolatey)
choco install ffmpegInstallation
From npm
npm install -g @s.lfr/mcp-coqui-ttsFrom Source
git clone https://github.com/yourusername/mcp-coqui-tts.git
cd mcp-coqui-tts
npm install
npm linkUsage
With Claude Desktop
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"coqui-tts": {
"command": "npx",
"args": ["@s.lfr/mcp-coqui-tts"]
}
}
}Or if installed from source:
{
"mcpServers": {
"coqui-tts": {
"command": "node",
"args": ["/path/to/mcp-coqui-tts/index.js"]
}
}
}Available Tools
1. speak
Convert text to speech with customizable parameters.
Parameters:
text(required): The text to convert to speechmodel: TTS model to use (default: "tts_models/en/ljspeech/tacotron2-DDC")output_path: Where to save the audio filespeaker_idx: Speaker index for multi-speaker modelslanguage_idx: Language index for multi-language modelsspeed: Speed factor (1.0 is normal speed)
Example:
{
"text": "Hello, this is a test of the text to speech system.",
"model": "tts_models/en/ljspeech/tacotron2-DDC",
"output_path": "/tmp/output.wav",
"speed": 1.2
}2. list_models
List all available TTS models.
Parameters: None
3. synthesize_long_text
Synthesize longer texts with automatic chunking and concatenation.
Parameters:
text(required): The long text to convertmodel: TTS model to useoutput_path: Where to save the final audiochunk_size: Maximum characters per chunk (default: 500)
Example:
{
"text": "This is a very long text that will be automatically split into chunks...",
"output_path": "/tmp/long_speech.wav",
"chunk_size": 500
}4. clone_voice
Clone a voice from an audio sample (requires XTTS model).
Parameters:
text(required): Text to speak in the cloned voicereference_audio(required): Path to reference audio for voice cloningoutput_path: Where to save the outputlanguage: Language code (default: "en")
Example:
{
"text": "This will be spoken in the cloned voice.",
"reference_audio": "/path/to/sample.wav",
"output_path": "/tmp/cloned_voice.wav",
"language": "en"
}Popular TTS Models
English Models
tts_models/en/ljspeech/tacotron2-DDC- High quality English TTStts_models/en/ljspeech/fast_pitch- Fast English TTStts_models/en/vctk/vits- Multi-speaker English (110 speakers)
Multilingual Models
tts_models/multilingual/multi-dataset/xtts_v2- Supports voice cloningtts_models/multilingual/multi-dataset/your_tts- Multilingual with voice cloning
Other Languages
Run list_models to see all available models for different languages.
Deployment on Smithery
To deploy this MCP server on Smithery:
Fork this repository
Connect your GitHub account to Smithery
Create a new MCP server on Smithery
Select this repository
Deploy
The server will be automatically available for use with any MCP-compatible client.
Development
Running Locally
npm startTesting
You can test the server using the MCP inspector:
npx @modelcontextprotocol/inspector node index.jsTroubleshooting
Common Issues
"tts: command not found"
Make sure Coqui TTS is installed:
pip install TTSEnsure Python/pip binaries are in your PATH
"ffmpeg: command not found"
Install ffmpeg for your operating system (see Prerequisites)
Model download fails
First run may take time as models are downloaded
Check internet connection
Ensure sufficient disk space (~1-5GB per model)
Voice cloning not working
Requires XTTS v2 model
Reference audio should be clear, 5-10 seconds long
WAV format recommended for reference audio
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
MIT
Acknowledgments
Coqui TTS for the excellent TTS library
Model Context Protocol for the MCP SDK
Support
For issues and questions, please open an issue on GitHub.
Available Tools
4 toolsclone_voiceB
Clone a voice from an audio sample (requires XTTS model)
Inputs: text (required), reference_audio (required), language, output_path.
list_modelsA
List available TTS models
Inputs: no named parameters.
speakC
Convert text to speech using Coqui TTS
Inputs: text (required), model, speed, output_path, +2 more.
synthesize_long_textB
Synthesize longer text with automatic chunking
Inputs: text (required), model, chunk_size, output_path.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Most tools are clearly distinct: list_models, clone_voice, and speak/synthesize_long_text target different actions. The only ambiguity is between speak and synthesize_long_text, though the long-text description clarifies the boundary.
All names use snake_case and are readable. The pattern is mostly verb_noun (list_models, synthesize_long_text, clone_voice), with 'speak' as a minor bare-verb deviation.
Four tools is well-scoped for a focused TTS server: model listing, standard synthesis, long-text synthesis, and voice cloning. Each tool earns its place without redundancy.
The core TTS lifecycle is covered: discovering models, synthesizing speech (standard and long), and cloning voices. Minor gaps exist around voice management or output options, but agents can work around them.
Related MCP Connectors
Text to speech and transcription for any AI model: MP3 voiceovers, audio and YouTube to text.
Text to speech in 200+ languages, voice cloning, voice design and SRT captions.
Text to speech in 149 languages: MP3 links from any assistant. Free without an account.
Generate English and Chinese speech, split long text, track batch jobs, and download audio.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to generate and play high-quality text-to-speech audio using the Kokoro model, with support for multiple voices, adjustable speaking speed, and audio caching.-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to convert text to high-quality speech audio using MeloTTS. Automatically splits long texts into segments, generates WAV files, and merges them using ffmpeg with support for multiple languages and customizable speech parameters.MIT
- FlicenseNot gradedqualityDmaintenanceEnables text-to-speech synthesis and voice cloning through GPT-SoVITS API integration. Supports multiple languages (Chinese, English, Japanese, Korean, Cantonese), dynamic model switching, and reference audio-based voice quality replication.4-
- AlicenseAqualityFmaintenanceEnables text-to-speech conversion using ElevenLabs API with voice management, streaming support, and multiple models.51MIT