Kokoro Text To Speech
Createdmberg
Generates MP3 files from text using the Kokoro-TTS model and optionally uploads them to S3.
About
Leverages the Kokoro-TTS model to convert text into speech, outputting high-quality MP3 audio files. It functions as an MCP server, providing a streamlined text-to-speech service with optional S3 integration for storage and distribution. Configuration is flexible, allowing customization of voice, speed, language, and S3 upload settings, making it suitable for a variety of applications requiring automated voice generation.
Key Features
- Allows customization of voice, speed, and language
- 0 GitHub stars
- Supports S3 upload with configurable credentials and bucket settings
- Includes a client script for easy TTS requests
- Generates MP3 audio files from text
- Provides options for local MP3 file storage and automatic cleanup
Use Cases
- Creating audio content from text sources
- Integrating TTS functionality into existing systems with S3 storage
- Automated voice generation for applications