F5-TTS

F5-TTS

Turns text into speech with the F5-TTS flow-matching model, shipped as F5-TTS and E2 TTS base checkpoints. For developers and researchers working under a non-commercial license.

Made by SWivid on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: F5-TTS is a text-to-speech model published by SWivid, and this repository holds its base checkpoints. It also carries a base checkpoint of E2 TTS. The linked paper describes the method as flow matching. The README gives no description of the model beyond the checkpoint layout, so this page stays short.

Who it suits: It suits speech researchers and developers who want public text-to-speech weights for non-commercial work.

Industry | Who uses it | How they use it | Example
Research | Speech researchers | Start from the published base checkpoints and the paper | Loading a base checkpoint to study its output
Software | Hobby developers | Add speech output to a personal project | A narration feature in a side project
Education | Students | Study how a public text-to-speech model is packaged | Setting up the checkpoint folder from scratch

You can skip it if you need commercial use, because the license is CC BY-NC 4.0.

Where to use it:

• Python, using the f5-tts library
• Windows, macOS or Linux, once the files are downloaded

Use case | Who | What they get back
Speech research | Researchers | Base checkpoints to start from
Personal projects | Developers | Spoken audio from written text
Model comparison | Students | F5-TTS and E2 TTS checkpoints side by side

How to set it up:

• Python, to run the Hugging Face download tool
• The huggingface_hub package
• The f5-tts library, which the project's own page describes

1. Install the Hugging Face hub package.
2. Download the repository files to your computer.
3. Place each checkpoint under a ckpts folder, in the layout shown below.

pip install -U huggingface_hub
hf download SWivid/F5-TTS

The card shows this folder layout for the checkpoints.

ckpts/
    F5TTS_v1_Base/
        model_1250000.safetensors
    F5TTS_Base/
        model_1200000.safetensors
    E2TTS_Base/
        model_1200000.safetensors

How to use it: The README shows no run command. It gives the checkpoint layout and points to the project's GitHub page and paper, so follow the project's own instructions to turn text into speech.

Tool | What it does
hf download | Fetches the checkpoint files to your computer
ckpts folder | Where the project expects the checkpoint files
F5TTS_v1_Base | The v1 base checkpoint of F5-TTS
F5TTS_Base | The base checkpoint of F5-TTS
E2TTS_Base | The base checkpoint of E2 TTS

Example: You download the repository, put the F5TTS_v1_Base checkpoint in its folder under ckpts, and follow the project's instructions to speak a sentence. You get audio of that sentence back.

For newcomers and experts: Text to speech turns written words into spoken audio. To start, download the files and arrange the ckpts folder exactly as shown, then read the project's instructions.

If you know the field, the paper frames F5-TTS around flow matching, and the repository stores three base checkpoints as Safetensors files named by training step. The README gives no training data or benchmarks, and the license excludes commercial use.

You download a base checkpoint
You place it under the ckpts folder
The f5-tts library loads it
Your text becomes speech

Good to know:

• Checkpoints: F5-TTS v1 base, F5-TTS base and E2 TTS base
• Variants: Hugging Face lists 8 quantized and 154 fine-tuned versions made by other people
• License: CC BY-NC 4.0
• Cost to run: none named
• Data it reaches: the text you give it, and the files you download from Hugging Face
• Not for: commercial use, since the license is non-commercial

On Hugging Face, 13 November 2026

• Task: text to speech
• Library: f5-tts
• Downloads in the last 30 days: 1,335,845
• Likes: 1,230
• License: cc-by-nc-4.0
• Quantized versions: 8
• Fine-tunes: 155
• Tags: f5-tts, text-to-speech

Links

• Model: https://huggingface.co/SWivid/F5-TTS
• Files: https://huggingface.co/SWivid/F5-TTS/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download SWivid/F5-TTS

Then follow the usage in its model card. Nothing in this kit runs by itself.