ai-models/IndexTTS-2
2
0
Fork 0
mirror of https://www.modelscope.cn/IndexTeam/IndexTTS-2.git synced 2026-04-02 19:52:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
indextts
2025-09-08 08:46:29 +00:00
parent 83a71ad75c
commit e6cb3a1f42
1 changed files with 0 additions and 34 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
README.md
View File

@ -1,15 +1,8 @@
<div align="center">
<img src='assets/index_icon.png' width="250"/>
</div>
## 👉🏻 IndexTTS2 👈🏻 ## 👉🏻 IndexTTS2 👈🏻
<center><h3>IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech</h3></center> <center><h3>IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech</h3></center>
[![IndexTTS2](assets/IndexTTS2_banner.png)](assets/IndexTTS2_banner.png)
<div align="center"> <div align="center">
<a href='https://arxiv.org/abs/2506.21619'> <a href='https://arxiv.org/abs/2506.21619'>
<img src='https://img.shields.io/badge/ArXiv-2506.21619-red?logo=arxiv'/> <img src='https://img.shields.io/badge/ArXiv-2506.21619-red?logo=arxiv'/>
@ -43,17 +36,6 @@ Existing autoregressive large-scale text-to-speech (TTS) models have advantages
**Tips:** Please contact authors for more detailed information. For commercial cooperation, please contact <u>indexspeech@bilibili.com</u> **Tips:** Please contact authors for more detailed information. For commercial cooperation, please contact <u>indexspeech@bilibili.com</u>
### Feel IndexTTS2
<div align="center">
**IndexTTS2: The Future of Voice, Now Generating**
[![IndexTTS2 Demo](assets/IndexTTS2-video-pic.png)](assets/IndexTTS2.mp4)
*Click the image to watch IndexTTS2 video*
</div>
### Contact ### Contact
QQ Group：553460296(No.1) 1048202584(No.2) 764630270(No.3)\ QQ Group：553460296(No.1) 1048202584(No.2) 764630270(No.3)\
Discord：https://discord.gg/uT32E7KDmy \ Discord：https://discord.gg/uT32E7KDmy \
@ -68,22 +50,6 @@ Emal：indexspeech@bilibili.com \
- `2025/03/25` 🔥 We release **IndexTTS-1.0** model parameters and inference code. - `2025/03/25` 🔥 We release **IndexTTS-1.0** model parameters and inference code.
- `2025/02/12` 🔥 We submitted our paper on arXiv, and released our demos and test sets. - `2025/02/12` 🔥 We submitted our paper on arXiv, and released our demos and test sets.
## 🖥️ Method
The overview of IndexTTS2 is shown as follows.
<picture>
<img src="assets/IndexTTS2.png" width="800"/>
</picture>
The key contributions of **indextts2** are summarized as follows:
- We propose a duration adaptation scheme for autoregressive TTS models. IndexTTS2 is the first autoregressive zero-shot TTS model to combine precise duration control with natural duration generation, and the method is scalable for any autoregressive large-scale TTS model.
- The emotional and speaker-related features are decoupled from the prompts, and a feature fusion strategy is designed to maintain semantic fluency and pronunciation clarity during emotionally rich expressions. Furthermore, a tool was developed for emotion control, utilising natural language descriptions for the benefit of users.
- To address the lack of highly expressive speech data, we propose an effective training strategy, significantly enhancing the emotional expressiveness of zeroshot TTS to State-of-the-Art (SOTA) level.
- We will publicly release the code and pre-trained weights to facilitate future research and practical applications.
## Acknowledge ## Acknowledge
1. [tortoise-tts](https://github.com/neonbjb/tortoise-tts) 1. [tortoise-tts](https://github.com/neonbjb/tortoise-tts)
2. [XTTSv2](https://github.com/coqui-ai/TTS) 2. [XTTSv2](https://github.com/coqui-ai/TTS)