Kokoro TTS
About
Converts text to speech using the Kokoro TTS engine with configurable voices, speeds, and languages, supporting both local storage and S3 cloud integration with automatic file cleanup.
Details
- Author
- mberg
- Repository
- mberg/kokoro-tts-mcp
- GitHub stars
- 24
- Downloads
- 234
- License
- Apache License 2.0
- Categories
- AI, Design, Developer Tools, File Management, Cloud Service, Frontend, Infrastructure, Other
Jump to
- Generates .mp3 files from text input
- Optional S3 upload for cloud storage
- Configurable voice, speed, and language
- Local MP3 retention and automatic cleanup
- Supports text input from file or argument
- Works with the Kokoro TTS model (ONNX)
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
Kokoro TTSCommand (node, npx, python, etc.)uvArguments-
Argument 1
--directory -
Argument 2
/path/toyourlocal/kokoro-tts-mcp -
Argument 3
run -
Argument 4
mcp-tts.py
Environment-
TTS_SPEED
1.0 -
TTS_VOICE
af_heart -
AWS_REGION
us-east-1 -
MP3_FOLDER
/path/to/mp3 -
S3_ENABLED
true -
TTS_LANGUAGE
en-us -
AWS_S3_FOLDER
mp3 -
AWS_ACCESS_KEY_ID
-
AWS_SECRET_ACCESS_KEY
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
send_text
Send a text request to the TTS server to generate speech. Parameters: text (string)
send_file
Send a request to the TTS server by reading text from a specified file. Parameters: file (string)
customize_voice_and_speed
Send a text request to the TTS server with customized voice and speed settings. Parameters: text (string), voice (optional string), speed (optional float)
disable_s3_upload
Send a text request to the TTS server and disable S3 upload for that request. Parameters: text (string), no-s3 (boolean)
help
Display help information for the TTS client command-line options.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"kokoro tts": {
"env": {
"TTS_SPEED": "1.0",
"TTS_VOICE": "af_heart",
"AWS_REGION": "us-east-1",
"MP3_FOLDER": "/path/to/mp3",
"S3_ENABLED": "true",
"TTS_LANGUAGE": "en-us",
"AWS_S3_FOLDER": "mp3",
"AWS_ACCESS_KEY_ID": "",
"AWS_SECRET_ACCESS_KEY": ""
},
"args": [
"--directory",
"/path/toyourlocal/kokoro-tts-mcp",
"run",
"mcp-tts.py"
],
"command": "uv"
}
}
}Linux
{
"env": {
"TTS_SPEED": "1.0",
"TTS_VOICE": "af_heart",
"AWS_REGION": "us-east-1",
"MP3_FOLDER": "/path/to/mp3",
"S3_ENABLED": "true",
"TTS_LANGUAGE": "en-us",
"AWS_S3_FOLDER": "mp3",
"AWS_ACCESS_KEY_ID": "",
"AWS_SECRET_ACCESS_KEY": ""
},
"args": [
"--directory",
"/path/toyourlocal/kokoro-tts-mcp",
"run",
"mcp-tts.py"
],
"command": "uv"
}Macos
{
"env": {
"TTS_SPEED": "1.0",
"TTS_VOICE": "af_heart",
"AWS_REGION": "us-east-1",
"MP3_FOLDER": "/path/to/mp3",
"S3_ENABLED": "true",
"TTS_LANGUAGE": "en-us",
"AWS_S3_FOLDER": "mp3",
"AWS_ACCESS_KEY_ID": "",
"AWS_SECRET_ACCESS_KEY": ""
},
"args": [
"--directory",
"/path/toyourlocal/kokoro-tts-mcp",
"run",
"mcp-tts.py"
],
"command": "uv"
}Windows
{
"env": {
"TTS_SPEED": "1.0",
"TTS_VOICE": "af_heart",
"AWS_REGION": "us-east-1",
"MP3_FOLDER": "/path/to/mp3",
"S3_ENABLED": "true",
"TTS_LANGUAGE": "en-us",
"AWS_S3_FOLDER": "mp3",
"AWS_ACCESS_KEY_ID": "",
"AWS_SECRET_ACCESS_KEY": ""
},
"args": [
"--directory",
"/path/toyourlocal/kokoro-tts-mcp",
"run",
"mcp-tts.py"
],
"command": "uv"
}<a href="https://glama.ai/mcp/servers/@mberg/kokoro-tts-mcp">
</a>
Kokoro Text to Speech (TTS) MCP Server
Kokoro Text to Speech MCP server that generates .mp3 files with option to upload to S3.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
