# F5-TTS vs SuperClonica: zero-shot cloning or fast CPU speech

Updated 2026-10-23

F5-TTS is an open text-to-speech model built on flow matching with a Diffusion Transformer, first released in October 2024 and followed by an improved v1 base model in March 2025. It clones voices zero-shot: give it a short reference clip and its text, and it speaks in that voice. SuperClonica works differently. A voice is trained once into a Supertonic 3 file, which then runs fast on an ordinary CPU.

If you want an F5-TTS alternative for CPU or for commercial use, here is what changes.

## How F5-TTS works

F5-TTS is a Diffusion Transformer with ConvNeXt V2, trained on about 100,000 hours of public multilingual data from the Emilia dataset. The official base model is the Chinese–English one. You pass a reference recording and its transcript; if the transcript is left empty, a speech recognition model fills it in at the cost of extra GPU memory.

The community has fine-tuned F5-TTS for other languages, and the repository links to those models. Our table counts the two languages of the official base model.

## F5-TTS speed on CPU and GPU

On a GPU F5-TTS is fast: the repository reports a real-time factor of 0.0402 with TensorRT-LLM and 0.1467 with PyTorch on a single NVIDIA L20 at 16 steps.

On CPU it is the slowest model in our table. The ZipVoice paper measured 37.284 at 32 steps on a single thread of a Xeon Platinum 8457C. Assuming a 2.5–7.5× effective gain from a modern 16-thread desktop CPU, we get 5–15× slower than real time: 50–150 seconds for a 10-second phrase. SuperClonica needs about 1.0–1.6 seconds.

## Quality and timbre stability

We rate F5-TTS 3 out of 5 for quality and 3 for timbre stability, against 4.5 and 5 for SuperClonica. Zero-shot cloning rebuilds the voice from the reference on every request, so the result depends on the clip you pass. A trained voice file gives you the same starting timbre every time.

## License: check before commercial use

The F5-TTS code is under MIT. The pre-trained models are licensed CC-BY-NC because of the Emilia training data, so the official weights cannot be used commercially under the default terms.

Supertonic 3 uses OpenRAIL-M, a royalty-free license with a list of prohibited uses rather than a non-commercial clause. Voices bought on SuperClonica are for your own projects and may not be resold.

## When to choose F5-TTS

Choose SuperClonica for products in the 31 Supertonic 3 languages, for CPU-only machines and for long texts where speed adds up. F5-TTS fits these cases:

- Research and non-commercial experiments with zero-shot cloning.
- Chinese or English speech on a GPU, or a community fine-tune for your language.
- A clone from a clip right now, with no training step.

## More on text to speech

- [Text-to-speech that runs on your own computer](https://superclonica.com/en/text-to-speech)
- [Supertonic vs SuperClonica: same model, faster and cleaner](https://superclonica.com/en/compare/supertonic)
- [Fish Audio and Fish Speech vs SuperClonica](https://superclonica.com/en/compare/fish-audio)
- [OmniVoice vs SuperClonica: more languages or more speed](https://superclonica.com/en/compare/omnivoice)
- [Qwen3-TTS vs SuperClonica for local text-to-speech](https://superclonica.com/en/compare/qwen3-tts)
- [VoxCPM 2 vs SuperClonica: studio sound or CPU speed](https://superclonica.com/en/compare/voxcpm)
- [An offline alternative to ElevenLabs](https://superclonica.com/en/compare/elevenlabs)
- [Kokoro TTS vs SuperClonica: two small models for local speech](https://superclonica.com/en/compare/kokoro)
- [Piper TTS vs SuperClonica: tiny devices or custom voices](https://superclonica.com/en/compare/piper)
- [Coqui XTTS-v2 vs SuperClonica: a Coqui TTS alternative](https://superclonica.com/en/compare/xtts)
- [Chatterbox TTS vs SuperClonica: instant cloning or a trained voice file](https://superclonica.com/en/compare/chatterbox)

## Text-to-speech guides

- [How to convert text to speech offline on your computer](https://superclonica.com/en/guides/offline-text-to-speech)
- [Voice cloning: how to get a voice that sounds like a recording](https://superclonica.com/en/guides/voice-cloning)
- [The best free text-to-speech models for local use in 2026](https://superclonica.com/en/guides/best-free-tts-models)
- [Text to speech for videos, audiobooks, games and apps](https://superclonica.com/en/guides/text-to-speech-for-videos)
- [Supertonic 3 voices: where to get custom voices and how to use them](https://superclonica.com/en/guides/supertonic-3-voices)
- [Text to speech in Python: offline, free and with natural voices](https://superclonica.com/en/guides/python-text-to-speech)
- [Self-hosted text-to-speech API in Docker](https://superclonica.com/en/guides/text-to-speech-api-docker)

## Frequently asked questions

### Can F5-TTS run on CPU?

Yes, but slowly. The ZipVoice paper measured a real-time factor of about 37 on a single CPU thread; our estimate for a 16-thread desktop CPU is 5–15× slower than real time.

### Can I use F5-TTS commercially?

Not with the official pre-trained models: they are CC-BY-NC because of their training data. The code itself is MIT.

### Which languages does F5-TTS support?

The official base model was trained on Chinese and English. Community fine-tunes add other languages, and their quality and licenses vary.

### What is a faster F5-TTS alternative for voice cloning?

If you can wait for training, a Supertonic 3 voice trained from your recording and run with SuperClonica: by our estimate 6.4–9.7× faster than real time on a desktop CPU. If you need cloning without training, look at Qwen3-TTS or OmniVoice, which clone from a few seconds of audio.

- [Try voices made for the CPU](https://superclonica.com/en/explore)
- [Install SuperClonica](https://superclonica.com/en/superclonica)

## Sources

- [F5-TTS repository (GitHub)](https://github.com/SWivid/F5-TTS)
- [F5-TTS model card (Hugging Face)](https://huggingface.co/SWivid/F5-TTS)
- [F5-TTS paper (arXiv)](https://arxiv.org/abs/2410.06885)
- [ZipVoice paper, table II: CPU speed](https://arxiv.org/html/2506.13053v1#S5.T2)
- [Supertonic 3 model card](https://huggingface.co/supertone-oss-archive/supertonic-3)
- [SuperClonica](https://superclonica.com/en/)
- [AI voice catalog for text to speech](https://superclonica.com/en/explore)
- [Custom voice commissions for Supertonic 3](https://superclonica.com/en/requests)
- [How it works: voices, local speech, training](https://superclonica.com/en/guide)
- [Install the faster Supertonic 3 engine](https://superclonica.com/en/superclonica)
- [About us: speech synthesis enthusiasts](https://superclonica.com/en/about)
- [Contacts, support and voice complaints](https://superclonica.com/en/contacts)
- [Privacy policy: what data we keep](https://superclonica.com/en/privacy)
- [Terms of use: rules for buyers and authors](https://superclonica.com/en/terms)
- [Text to speech](https://superclonica.com/en/text-to-speech)