---
title: FireRedTTS3
canonical_url: "https://www.modelscope.cn/studios/FireRedTeam/FireRedTTS3"
md_url: "https://www.modelscope.cn/studios/FireRedTeam/FireRedTTS3.md"
repository: FireRedTeam/FireRedTTS3
chinese_name: FireRedTTS3
last_updated: 2026-08-26
sdk_type: gradio
sdk_version: 6.17.3
downloads: 0
stars: 42
---

# FireRedTTS3

> FireRedTTS3 - FireRedTeam 在 ModelScope 创建的在线 Demo。FireRedTTS3 统一语音生成与编辑：零样本语音克隆、音色设计、语音编辑，基于Modelscope xGPU

FireRedTeam/FireRedTTS3 是 ModelScope 魔搭社区上的在线可交互 Demo（创空间），基于 gradio 6.17.3 构建。

- **Repository**: FireRedTeam/FireRedTTS3
- **SDK**: gradio
- **SDK version**: 6.17.3
- **Downloads**: 0
- **Stars**: 42
- **Last updated**: 2026-08-26

Source: https://www.modelscope.cn/studios/FireRedTeam/FireRedTTS3

---

# 🔥 FireRedTTS3

Interactive demo of [FireRedTeam/FireRedTTS3](https://modelscope.cn/models/FireRedTeam/FireRedTTS3),
a unified speech generation and editing model (Qwen3-1.7B backbone + flow-matching
head over the continuous RedAE audio autoencoder, 24 kHz).

Three tabs:

| Tab | Checkpoint | What it does |
| --- | --- | --- |
| 🎙️ Voice Cloning | `fireredtts3_base` | Zero-shot cloning from a short reference clip — 24 languages and 21 Chinese dialects |
| 🎨 Voice Design | `fireredtts3_instruct` | Creates a voice from a natural-language description, no reference audio |
| ✂️ Speech Editing | `fireredtts3_instruct` | Semantic edits (insert / delete / substitute words) and acoustic edits (speed, pitch, volume) |

Text normalization runs locally via `wetext` (Chinese / English); automatic language
routing uses fastText `lid.176` (bundled in this repo). The optional LLM-based
normalizer from the upstream repo is disabled here (it requires external API
credentials).

This studio is an unofficial migration of the
[Hugging Face Space](https://huggingface.co/spaces/hugging-apps/firered-tts3):
ZeroGPU scheduling removed, weights downloaded from the official ModelScope
mirror at startup and cached for persistence.

## Credits

- Model and inference code: [FireRedTeam/FireRedTTS3](https://github.com/FireRedTeam/FireRedTTS3), Apache-2.0.
- `examples/en_prompt.wav`: from [OpenBMB/VoxCPM](https://github.com/OpenBMB/VoxCPM) (`examples/example.wav`), Apache-2.0.
- `examples/zh_prompt.wav`: from [FireRedTeam/FireRedTTS2](https://github.com/FireRedTeam/FireRedTTS2) (`examples/chat_prompt/zh/S2.flac`), Apache-2.0.

Voice cloning is provided for academic research purposes only — do not use it for
impersonation or any illegal activity.