F5-TTS
github.com
NewOpen sourceNo card
Open-source flow-matching text-to-speech model with voice cloning
- Free tier
- Yes
- Per month
- Free
- MCP
- No
Why it's here
Free self-hosted TTS with voice cloning; GPU deployment and license checks make shipping less turnkey.
Free tier
Free model weights and local inference
Visit F5-TTS(opens in a new tab)
Last verified
Audio
#21 of 25Free self-hosted TTS with voice cloning; GPU deployment and license checks make shipping less turnkey.
| per month | Open sourceFreeYou supply GPU or CPU compute |
|---|---|
| Commercial use | |
| API access | |
| Voice cloning | |
| Real-time | |
| Speech-to-text | |
| Music generation | |
| Diarization | |
| Stems / WAV | |
| Languages | 10 languages |