F5-TTS
Well-known open model that clones a voice from seconds of audio.
FreeOpenRuns on your PC
- Best for
- Hobby voice cloning
- On your PC
- Technical
- Works on
- Windows, Mac, Linux
- License
- CC-BY-NC-4.0
What’s good
- Clones from a short reference clip
- Simple web app included
Downsides
- Non-commercial license for the model weights
- Older; Qwen3-TTS and Chatterbox are newer and commercial
- No consent check of any kind
At a glance.
- Best for
- Hobby voice cloning
- Price
- Free, open source
- Version
- F5-TTS v1Released 2025-03
- Works on
- Windows, Mac, Linux
- Open source
- Yes, CC-BY-NC-4.0
- Made by
- SWivid (SJTU research)
- Website
- github.com
Should you use it?
It is #10 of 10. Good for hobby voice cloning; for most people, ElevenLabs Voice Cloning is the better start.
Can I run it myself?
Yes. Technical: command line or python.
Use f5-tts Python package with Gradio app.
- You need
- NVIDIA GPU recommended; works on Apple Silicon
- Setup
- TechnicalCommand line or Python
- Laptop, 8 GBToo small
- PC, 16 GB+Too small
- Mac, 16 GBRuns
- Mac, 32 GBRuns
- Mac, 64 GB+Runs
- PC, 8 GB GPURuns
- PC, 12 GB GPURuns
- PC, 16 GB GPURuns
- PC, 24 GB GPURuns
- WorkstationRuns