Chatterbox

• Source: https://github.com/resemble-ai/chatterbox
• License: MIT
• Alternatives: Speaches, Piper, Coqui TTS, ElevenLabs

Text-to-speech (TTS) service for generating audio from text.

Features

• Voice Cloning: Clone a voice from a short reference audio clip with no fine-tuning
• Expressive Synthesis: Emotion and style controllable output beyond monotone TTS
• High-Quality Audio: Neural model producing natural-sounding speech
• Self-Hosted: Runs locally on CPU or GPU — no external API calls
• Open Source: MIT-licensed model from Resemble AI