Chatterbox TTS
Previously listed as free · not rechecked
Generate expressive, multilingual speech from a short voice reference with an open local model.
Audio & Voice
Audio & Voice Checked Oct 1, 2026
F5-TTS
Turn text and a permitted reference clip into expressive speech using an open research implementation.
Best for: Developers and researchers experimenting with local TTS, voice conditioning, or speech pipelines.
Access
Previously listed as The F5-TTS repository is MIT licensed and provides code, packages, Docker options, and downloadable checkpoints. The official F5-TTS model card lists the model license as CC-BY-NC-4.0, so commercial or monetized use needs a separate rights review. Local inference needs Python, audio dependencies, and suitable hardware; the model is not currently deployed by a Hugging Face inference provider.
Useful?
What you can do with it
- Prototype narration
- Compare open TTS models
- Test voice conditioning
- Build a local speech demo
- Study flow-matching speech generation
Good to know
- MIT codebase
- Local inference and Docker paths
- Expressive speech generation
- Reference-audio conditioning
Limitations
- Model is CC-BY-NC-4.0
- Technical setup
- Local hardware is required
Other official links
Keep exploring
Similar tools
FreeTTS
Previously listed as free tier · not rechecked
A browser audio toolkit for text-to-speech, speech-to-text, vocal removal, voice enhancement, and quick editing.
Audio & Voice
Kokoro-82M
Previously listed as free · not rechecked
Generate natural speech locally or in a public demo with a small open-weight TTS model.
Audio & Voice