---
id: "b889"
language: "en"
library: "tools"
official_url: "https://github.com/SWivid/F5-TTS"
profile_updated_on: "2026-10-22"
---

# F5-TTS

Generate speech from reference audio, its transcript and target text, with chunked inference, multi-voice sequences and fine-tuning.

- Company / organization: F5-TTS project
- Category: Audio & music
- Official website: [https://github.com/SWivid/F5-TTS](https://github.com/SWivid/F5-TTS)
- Profile updated: 2026-10-22


## Overview

F5-TTS conditions new speech on reference audio and its transcript. Command-line and Gradio workflows support chunked synthesis, multiple styles and speakers, plus training and fine-tuning. Omitting the reference transcript invokes an additional recognition model. Code uses MIT, while official pretrained weights use non-commercial CC-BY-NC terms; code, weights and training data have distinct usage conditions.

## Official sources and references

- [Official website](https://github.com/SWivid/F5-TTS)
- [Documentation](https://huggingface.co/SWivid/F5-TTS)

## Reading & subscriptions

- [Interactive profile](../../../products/f5-tts--b889.html)
- [Read](../../../read/en/products/f5-tts--b889.html)
- [JSON](../../../read/en/products/f5-tts--b889.json)

Descriptions summarize public information; consult official websites for features, pricing and regional availability.