Kokoro TTS MCP is a server that converts text to speech using the Kokoro TTS engine, generating MP3 files with optional S3 upload capabilities. The implementation provides a robust text-to-speech service with configurable voices, speech speed, and language options, while handling file management through local storage or cloud integration. Built with fallback mechanisms for when the primary TTS engine is unavailable, it includes features like automatic cleanup of old files and markdown text preprocessing. This server is particularly valuable for applications requiring high-quality voice synthesis without leaving the AI assistant interface, such as content creation, accessibility tools, or voice-enabled applications.
Aún no hay reseñas. ¡Sé el primero en reseñar!
Inicia sesión para unirte a la conversación
Highlight AISend a text-to-speech request to the server with parameters: --text (string), --file (optional string), --voice (optional string), --speed (optional float), --no-s3 (optional flag to disable S3 upload)
Set the folder path for storing MP3 files using the environment variable MP3_FOLDER.
Automatically delete MP3 files older than a specified number of days by setting MP3_RETENTION_DAYS.
Delete local MP3 files immediately after a successful S3 upload by setting DELETE_LOCAL_AFTER_S3_UPLOAD to true.
Enable S3 uploads by setting S3_ENABLED to true.
Disable S3 uploads with the client option --no-s3.
