Model
F5-TTS
F5-TTS is an open-weight AI model, released in 2024, made for developers.
A text-to-speech model based on flow matching that clones a voice from a short sample.
Main jobs: Text to speech, Voice cloning. It is open source and free to use. You can use it offline on your own machine, on your own server, in the terminal and through an API.
Markdown version of https://godooo.ai/en/model/f5-tts. Every page on this site has one: add .md to its address.
At a glance
- Type
- Model
- Released
- 2024
- Galaxy
- Voice & Music
- Open source
- Yes · MIT
- Source code
- github.com/SWivid/F5-TTS
- GitHub stars
- 15,278
- How you run it
- Runs offline · Self-host · Terminal · API
- Made for
- Developers
- Website
- github.com
What it can do
Text to speechmain jobunconfirmed
“Basic TTS with Chunk Inference”— github.com, 2026-09-24
Voice cloningmain jobunconfirmed
“F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching”— github.com, 2026-09-24
unconfirmedproposed by a machine, awaiting calibration
Alternatives
- ElevenLabsFree plan + paid upgradesAlso does: Text to speech, Voice cloning; no code needed
- ChatterboxOpen source, freeAlso does: Text to speech, Voice cloning
- CosyVoiceOpen source, freeAlso does: Text to speech, Voice cloning
- Fish SpeechOpen source, freeAlso does: Text to speech, Voice cloning
- GPT-SoVITSOpen source, freeAlso does: Text to speech, Voice cloning; no code needed
- CapCut 剪映Free plan + paid upgradesAlso does: Text to speech, Voice cloning; no code needed
- DescriptFree plan + paid upgradesAlso does: Text to speech, Voice cloning; no code needed
- ChatTTSOpen source, freeAlso does: Text to speech
- RVCOpen source, freeAlso does: Voice cloning; no code needed
- WaveNetAlso does: Text to speech
- HeyGenFree plan + paid upgradesAlso does: Voice cloning; no code needed
- MoneyPrinterTurboOpen source, freeAlso does: Text to speech; no code needed
Connections
- Applies
- Voice Cloning
Questions
What is F5-TTS?
F5-TTS is an open-weight AI model, released in 2024, made for developers. A text-to-speech model based on flow matching that clones a voice from a short sample.
Is F5-TTS free?
Yes. F5-TTS is open source (MIT) and free to use.
Is F5-TTS open source?
Yes, under the MIT license. The source code is at https://github.com/SWivid/F5-TTS.
Can F5-TTS run locally?
Yes. F5-TTS can run offline on your own machine. It can also be self-hosted on your own server.
What can F5-TTS do?
Main jobs: Text to speech, Voice cloning.
What are open-source alternatives to F5-TTS?
Open-source ones: Chatterbox, CosyVoice, Fish Speech, GPT-SoVITS, ChatTTS, RVC and MoneyPrinterTurbo. Others: ElevenLabs, CapCut 剪映, Descript, WaveNet and HeyGen.
Sources
- github.com/SWivid/F5-TTSchecked 2026-09-24