AI · AI model
Chatterbox
Open-source zero-shot text-to-speech and voice cloning model
Chatterbox is an open-source text-to-speech model from Resemble AI designed for expressive, zero-shot voice cloning. It can mimic a target voice from just a few seconds of reference audio while providing control over emotional intensity. It runs faster than real time and includes built-in audio watermarking.
What it's for
- Clone a speaker's voice using a short reference audio sample
- Generate spoken voiceovers with adjustable emotional intensity
- Synthesize real-time speech locally or in self-hosted pipelines
Features
- Zero-shot voice cloning from roughly 5 seconds of audio
- Expressive emotion intensity adjustment
- Faster-than-real-time speech synthesis inference
- Integrated PerTh audio watermarking for safety and detection
- Interactive web demo on Hugging Face Spaces
Pricing
Open source. Free and open source
Details
- Type
- AI model
- Category
- AI
- Topic
- Text to Speech
- Open source
- Yes
- Platforms
- Web, Self-hosted
- For
- Developers, creators, and AI researchers looking for self-hosted voice cloning
- Alternative to
- ElevenLabs, Bark, XTTS
- Tags
- tts, voice cloning, audio, open source, huggingface, ai speech
Why it was saved
- @AiBreakfast: Zero-shot voice cloning from 5 seconds of audio; emotion intensity control from subtle to dramatic; real-time synthesis faster than real-time inference; built-in audio watermarking; preferred over ElevenLabs in blind evaluations
Compare
Related
AI voice generator, voice cloning, and conversational agent platform
Ultra-low-latency streaming text-to-speech and instant voice cloning model.
Open-source 1.6B text-to-speech model generating multi-speaker dialogue in one pass.
Fast, low-cost text-to-speech API and studio for creators and developers
Converts spoken thoughts into structured, polished writing in customizable styles.
Official Python library for Cartesia's real-time text-to-speech API
Updated