👉🏻 IndexTTS2 👈🏻
IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
Abstract
Existing autoregressive large-scale text-to-speech (TTS) models have advantages in speech naturalness, but their token-by-token generation mechanism makes it difficult to precisely control the duration of synthesized speech. This becomes a significant limitation in applications requiring strict audio-visual synchronization, such as video dubbing. This paper introduces IndexTTS2, which proposes a novel, general, and autoregressive model-friendly method for speech duration control. The method supports two generation modes: one explicitly specifies the number of generated tokens to precisely control speech duration; the other freely generates speech in an autoregressive manner without specifying the number of tokens, while faithfully reproducing the prosodic features of the input prompt. Furthermore, IndexTTS2 achieves disentanglement between emotional expression and speaker identity, enabling independent control over timbre and emotion. In the zero-shot setting, the model can accurately reconstruct the target timbre (from the timbre prompt) while perfectly reproducing the specified emotional tone (from the style prompt). To enhance speech clarity in highly emotional expressions, we incorporate GPT latent representations and design a novel three-stage training paradigm to improve the stability of the generated speech. Additionally, to lower the barrier for emotional control, we designed a soft instruction mechanism based on text descriptions by fine-tuning Qwen3, effectively guiding the generation of speech with the desired emotional orientation. Finally, experimental results on multiple datasets show that IndexTTS2 outperforms state-of-the-art zero-shot TTS models in terms of word error rate, speaker similarity, and emotional fidelity. Audio samples are available at: IndexTTS2 demo page
Tips: Please contact authors for more detailed information. For commercial cooperation, please contact indexspeech@bilibili.com
Feel IndexTTS2
IndexTTS2: The Future of Voice, Now Generating
Click the image to watch IndexTTS2 video
Contact
QQ Group：553460296(No.1) 1048202584(No.2) 764630270(No.3)
Discord：https://discord.gg/uT32E7KDmy
Emal：indexspeech@bilibili.com
欢迎大家来交流讨论！
📣 Updates
2025/09/08🔥🔥🔥 We release the IndexTTS-2- The first autoregressive TTS model with precise synthesis duration control: supporting both controllable and uncontrollable modes
- The model achieves highly expressive emotional speech synthesis, with emotion-controllable capabilities enabled through multiple input modalities.
2025/05/14🔥🔥 We release the IndexTTS-1.5, Significantly improve the model's stability and its performance in the English language.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.
🖥️ Method
The overview of IndexTTS2 is shown as follows.
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.
Model Download
| HuggingFace | ModelScope |
|---|---|
| 😁 IndexTTS2 | IndexTTS-2 |
| IndexTTS-1.5 | IndexTTS-1.5 |
| IndexTTS | IndexTTS |
Usage Instructions
Environment Setup
- Download this repository:
git clone https://github.com/index-tts/index-tts.git
- Install dependencies:
conda create -n indextts2 python=3.10
conda activate indextts2
pip install -r requirements.txt
- Download models:
Download by huggingface-cli:
huggingface-cli download IndexTeam/IndexTTS-1.5 \
config.yaml bigvgan_discriminator.pth bigvgan_generator.pth bpe.model dvae.pth gpt.pth unigram_12000.vocab \
--local-dir checkpoints
Recommended for China users. 如果下载速度慢，可以使用镜像：
export HF_ENDPOINT="https://hf-mirror.com"
Or by wget:
wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/bigvgan_discriminator.pth -P checkpoints
wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/bigvgan_generator.pth -P checkpoints
wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/bpe.model -P checkpoints
wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/dvae.pth -P checkpoints
wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/gpt.pth -P checkpoints
wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/unigram_12000.vocab -P checkpoints
wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/config.yaml -P checkpoints
- Run test script:
Do a quick test run
from indextts.infer_indextts2 import IndexTTS2
tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", is_fp16=False, use_cuda_kernel=False)
text="这是一个有很好情感表现力的自回归语音生成大模型，它还可以控制合成语音的时长，希望能受到大家的喜欢。"
tts.infer(spk_audio_prompt='test_data/input.wav', text=text, output_path="gen.wav", verbose=True)
额外指定一个情感参考音频 Specify an additional emotional reference audio
from indextts.infer_indextts2 import IndexTTS2
tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", is_fp16=False, use_cuda_kernel=False)
text="这是一个有很好情感表现力的自回归语音生成大模型，它还可以控制合成语音的时长，希望能受到大家的喜欢。"
tts.infer(spk_audio_prompt='test_data/input.wav', text=text, output_path="gen.wav", emo_audio_prompt="test_data/low.wav", verbose=True)
当指定情感参考音频时，还可以额外指定参数emo_alpha，emo_alpha代表参考情感音频的程度，默认为1.0
from indextts.infer_indextts2 import IndexTTS2
tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", is_fp16=False, use_cuda_kernel=False)
text="这是一个有很好情感表现力的自回归语音生成大模型，它还可以控制合成语音的时长，希望能受到大家的喜欢。"
tts.infer(spk_audio_prompt='test_data/input.wav', text=text, output_path="gen.wav", emo_audio_prompt="test_data/low.wav", emo_alpha=0.5, verbose=True)
也可以不指定情感参考音频，而给定各基础情感(喜|怒|哀|惧|厌恶|低落|惊喜|平静)的强度，包括8个float的list
from indextts.infer_indextts2 import IndexTTS2
tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", is_fp16=False, use_cuda_kernel=False)
text="这是一个有很好情感表现力的自回归语音生成大模型，它还可以控制合成语音的时长，希望能受到大家的喜欢。"
tts.infer(spk_audio_prompt='test_data/input.wav', text=text, output_path="gen.wav", emo_vector=[0, 1.0, 0, 0, 0, 0, 0, 0], verbose=True)
可以使用文本情感描述指导情感的合成，使用参数use_emo_text
from indextts.infer_indextts2 import IndexTTS2
tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", is_fp16=False, use_cuda_kernel=False)
text="这是一个有很好情感表现力的自回归语音生成大模型，它还可以控制合成语音的时长，希望能受到大家的喜欢。"
tts.infer(spk_audio_prompt='test_data/input.wav', text=text, output_path="gen.wav", use_emo_text=True, verbose=True)
当不指定emo_text，根据输入的合成文案内容推理，指定时根据指定的文案推
from indextts.infer_indextts2 import IndexTTS2
tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", is_fp16=False, use_cuda_kernel=False)
text="这是一个有很好情感表现力的自回归语音生成大模型，它还可以控制合成语音的时长，希望能受到大家的喜欢。"
tts.infer(spk_audio_prompt='test_data/input.wav', text=text, output_path="gen.wav", use_emo_text=True, emo_text='有一丢丢伤心', verbose=True)
Specify the duration of the synthesized speech
from indextts.infer_indextts2 import IndexTTS2
tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", is_fp16=False, use_cuda_kernel=False)
text="这是一个有很好情感表现力的自回归语音生成大模型，它还可以控制合成语音的时长，希望能受到大家的喜欢。"
tts.infer(spk_audio_prompt='test_data/input.wav', text=text, output_path="gen.wav", use_speed=True, target_dur=7.5, verbose=True)
- Use as command line tool:
# Make sure pytorch has been installed before running this command
pip install -e .
indextts "大家好，我现在正在bilibili 体验 ai 科技，说实话，来之前我绝对想不到！AI技术已经发展到这样匪夷所思的地步了！" \
--voice reference_voice.wav \
--model_dir checkpoints \
--config checkpoints/config.yaml \
--output output.wav
Use --help to see more options.
indextts --help
Web Demo
pip install -e ".[webui]"
python webui.py
# use another model version:
python webui.py --model_dir IndexTTS-1.5
Open your browser and visit http://127.0.0.1:7860 to see the demo.
Note for Windows Users
On Windows, you may encounter an error when installing pynini:
ERROR: Failed building wheel for pynini
In this case, please install pynini via conda:
# after conda activate index-tts
conda install -c conda-forge pynini==2.1.5
pip install WeTextProcessing==1.0.3
pip install -e ".[webui]"
Sample Code
from indextts.infer import IndexTTS
tts = IndexTTS(model_dir="checkpoints",cfg_path="checkpoints/config.yaml")
voice="reference_voice.wav"
text="大家好，我现在正在bilibili 体验 ai 科技，说实话，来之前我绝对想不到！AI技术已经发展到这样匪夷所思的地步了！比如说，现在正在说话的其实是B站为我现场复刻的数字分身，简直就是平行宇宙的另一个我了。如果大家也想体验更多深入的AIGC功能，可以访问 bilibili studio，相信我，你们也会吃惊的。"
tts.infer(voice, text, output_path)
👉🏻 IndexTTS 👈🏻
IndexTTS2: [Paper]; [Demo]; [ModelScope]; [HuggingFace]
IndexTTS1: [Paper]; [Demo]; [ModelScope]; [HuggingFace]
Acknowledge
📚 Citation
🌟 If you find our work helpful, please leave us a star and cite our paper.
IndexTTS2
@article{zhou2025indextts2,
title={IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech},
author={Siyi Zhou, Yiquan Zhou, Yi He, Xun Zhou, Jinchao Wang, Wei Deng, Jingchen Shu},
journal={arXiv preprint arXiv:2506.21619},
year={2025}
}
IndexTTS
@article{deng2025indextts,
title={IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System},
author={Wei Deng, Siyi Zhou, Jingchen Shu, Jinchao Wang, Lu Wang},
journal={arXiv preprint arXiv:2502.05512},
year={2025},
doi={10.48550/arXiv.2502.05512},
url={https://arxiv.org/abs/2502.05512}
}