Chatterbox

概要

Chatterbox simplifies text-to-speech generation by exposing the Chatterbox TTS model through a streamlined tool. It automatically loads the model, manages temporary files, and handles audio playback, providing real-time progress notifications to keep users informed throughout the process. The server offers configurable audio file storage with automatic cleanup and supports various hardware acceleration options for optimized performance.

主な機能

• Configurable audio file storage and cleanup
• Hardware acceleration support (MPS, CUDA, CPU)
• Automatic model loading with progress notifications
• 3 GitHub stars
• Generates speech using temporary files (auto-cleanup)
• Plays audio automatically on macOS using `afplay`

ユースケース

• Creating accessible content from text
• Integrating text-to-speech into LLM workflows
• Generating audio prompts for applications