compare
F5-TTS vs Fish Speech
The same facts for both, read from GitHub every night, and the relation a person reviewed.
| Fact | F5-TTS | Fish Speech |
|---|---|---|
| Language | Python | Python |
| Licence | MIT | Other |
| Stars | 15k | 33k |
| Latest | 1.1.22 | v1.5.1 |
| Last push | 2026-09-21 | 2026-10-05 |
| Release cadence | about 20 days between releases | about 35 days between releases |
| Active contributors | 3 commit authors on the default branch in the last 90 days | 5 commit authors on the default branch in the last 90 days |
| Flags | none | none |
How they relate
Both replace ElevenLabs. Alternatives to ElevenLabs →
PartialF5-TTSVoice cloning from a short reference clip, with a Gradio app.
PartialFish SpeechMultilingual TTS with voice cloning, under a non-commercial licence.
F5-TTS
- 1.1.222026-07-23fix: allocate fix_duration across chunks to avoid N× duration blow-up
- 1.1.212026-07-05update gradio>=6.15.0 in pyproject.toml
- 1.1.202026-04-20fix: refactor cache handling in DiT, MMDiT, and UNetT classes (lazyinit to avoid EMA deepcopy failure while training)
- 1.1.192026-04-16reuse resamplers and cache vocos MelSpectrogram instances
- 1.1.182026-03-24Add Arabic model details to SHARED.md
Fish Speech
- v2.0.0-beta2026-03-10Fish Audio S2 Betapre-release
- v1.5.12025-05-31V1.5.1
- v1.5.02024-12-25V1.5.0
- v1.4.32024-11-29V1.4.3
- v1.4.22024-10-25V1.4.2
F5-TTS
✓ signed The latest release, 1.1.22, carries a signature GitHub verified.
Loading the security report
Fish Speech
✓ signed The latest release, v1.5.1, carries a signature GitHub verified.
Loading the security report