TTS MCP
About
Text-to-Speech protocol server that synthesizes text from LLMs and plays audio natively through the host system's desk speakers.
Details
- Author
- leo9iota
- Downloads
- 407
- Categories
- Developer Tools, Other, AI
Jump to
- Direct playback of synthesized audio through host system speakers.
- Aggregates multiple TTS providers into individual command tools.
- Persona routing maps voices and providers to semantic names.
- Caches generated audio artifacts locally to an XDG cache directory.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
TTS MCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Download the pre-compiled binary for your OS from the Releases page, or build from source with Go 1.22+ via just init. Configure API keys in a .env file located in your standard OS configuration directory (e.g., ~/.config/tts-mcp/.env on Linux) using either the tts-mcp-config CLI or manual editing. Then attach the server as a command-line MCP tool in your preferred AI editor, such as Claude Desktop, Cursor, or Antigravity.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"tts mcp": {
"tts-mcp": {
"command": "/absolute/path/to/extracted/tts-mcp",
"args": [],
"env": {
"FISH_AUDIO_API_KEY": "<OPTIONAL_KEY>",
"ELEVENLABS_API_KEY": "<OPTIONAL_KEY>"
}
}
}
}
}McpServers
{
"tts-mcp": {
"command": "/absolute/path/to/extracted/tts-mcp",
"args": [],
"env": {
"FISH_AUDIO_API_KEY": "<OPTIONAL_KEY>",
"ELEVENLABS_API_KEY": "<OPTIONAL_KEY>"
}
}
}MCP server that provides Text-to-Speech capabilities. It accepts text output from LLMs, synthesizes it using remote or local audio providers, and plays it directly through the host system's native speakers.
- Direct Playback: Pipes synthesized audio to the host system natively.
- Provider Aggregation: Automatically exposes individual command tools for any configured TTS provider.
- Persona Routing: Map specific voices and providers to semantic names to simplify LLM tool calls.
- Caching: Saves generated audio artifacts locally to an XDG cache directory.
- FishAudio
- ElevenLabs
- Neets AI
- PlayHT
- Cartesia
- OpenAI
- Azure
- Local APIs
Requires Go 1.22+ to build from source viajust init
Download the pre-compiled binaries matching your OS from theReleasespage.
tts-mcprequires an.envfile in your standard OS configuration directory:
- Windows:%APPDATA%\tts-mcp\.env
- Linux:~/.config/tts-mcp/.env
- macOS:~/Library/Application Support/tts-mcp/.env
Run the includedtts-mcp-configCLI to safely initialize this file, or populate it manually:
FISHAUDIO_API_KEY="<YOUR_API_KEY_HERE>" ELEVENLABS_API_KEY="<YOUR_API_KEY_HERE>"
You can attach the server as a standard command-line MCP tool in your preferred AI editor.
Add the executable to your MCP Servers configuration list:
- Name:tts-mcp
- Type:command
- Command:/absolute/path/to/extracted/tts-mcp
Append to yourclaude_desktop_config.json:
{ "mcpServers": { "tts-mcp": { "command": "/absolute/path/to/extracted/tts-mcp" } } }
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
AI-powered text-to-speech MCP server with instant voice cloning. Generate speech from Claude Desktop, Claude Code, or n8n using 5 built-in voices (English, German, French, Spanish) or clone any voice from a short audio sample. Runs fully local, no API keys, no cloud. Supports stdio, SSE, and HTTP transports.
Model Context Protocol (MCP) server for Kokoro text-to-speech with female voice. 100% local, no Python required. Supports SSE and stdio transports.
Converts text summaries to speech using OpenAI's Text-to-Speech API and plays them in the background.
Give any LLM agent a real Android or iPhone as its body — 62 MCP tools for tap, swipe, type, screenshot, app launch, camera, TTS, on-device inference, and batched automation.
Interact with MiniMax's powerful APIs for text-to-speech, voice cloning, and video/image generation.
A JavaScript/TypeScript server for MiniMax MCP, offering image/video generation, text-to-speech, and voice cloning.
MCP server exposing the full Mistral AI surface (chat, OCR, Codestral FIM, Voxtral audio, vision, agents, moderation, classification, files, batch). Stdio + Streamable HTTP, BYOK with Mistral's free 1B tokens/month
Local, on-device TTS for Claude & Cursor. No API key, no cloud. 10 voices, 31 languages, ~820ms on Apple Silicon.
An AI voice toolkit with TTS, voice cloning, and video translation, now available as an MCP server for smarter agent integration.
Generate high-quality text-to-speech and text-to-voice outputs using the DAISYS platform.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
