An Industrial-Level Controllable and Efficient Zero-Shot Text-to-Speech System

简体中文 | English | 日本語 | Español | العربية

IndexTTS is a zero-shot text-to-speech system that clones a voice from a single reference audio clip. The latest release, IndexTTS-2.5, supports Chinese, English, Japanese, Spanish and Arabic, with fine-grained emotion control, speaking speed control, pronunciation control (Pinyin / CMU phonemes / Japanese Kana), and faster inference than IndexTTS-2.

Model	Demos	Paper	ModelScope	HuggingFace
IndexTTS-2.5
IndexTTS-2
IndexTTS-1.5
IndexTTS

• 2026/08/10 🔥 We release IndexTTS-2.5
  • Now supports Chinese, English, Japanese, Spanish and Arabic, with faster inference than IndexTTS-2, while keeping the cross-lingual and timbre-emotion disentanglement capabilities.
  • Improved controllability of Chinese Pinyin, English CMU phonemes and Japanese Kana.
  • Speaking speed control via duration_factor (0.5x–2.0x duration).
  • Production deployment supported via vLLM.
• 2025/09/08 🔥 We release IndexTTS-2
  • The first autoregressive TTS model with precise synthesis duration control, supporting both controllable and uncontrollable modes. This functionality is not yet enabled in this release.
  • Highly expressive emotional speech synthesis, with emotion control through multiple input modalities.
• 2025/05/14 🔥 We release IndexTTS-1.5, significantly improving the model's stability and its performance in English.
• 2025/03/25 🔥 We release IndexTTS-1.0 with model weights and inference code.
• 2025/02/12 🎉 We submitted our paper to arXiv, and released our demos and test sets.

Make sure you have git installed, then download this repository:

git clone https://github.com/index-tts/index-tts.git && cd index-tts

Example audio files are downloaded on demand from HuggingFace/ModelScope the first time the WebUI starts, so Git LFS is no longer required.

We use uv to manage the project's dependency environment. It is required for a reliable installation:

pip install -U uv  # or see the link above for other install methods

uv sync --all-extras

This automatically creates a .venv project directory and installs the correct versions of Python and all required dependencies.

If the download is slow, use a local mirror, e.g. one of these mirrors in China:

uv sync --all-extras --default-index "https://mirrors.aliyun.com/pypi/simple"

uv sync --all-extras --default-index "https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"

Download the required models via uv tool:

Via huggingface-cli:

uv tool install "huggingface-hub"

# IndexTTS-2.5
hf download IndexTeam/IndexTTS-2.5 --local-dir=checkpoints

# IndexTTS-2
hf download IndexTeam/IndexTTS-2 --local-dir=checkpoints_2

Or via modelscope:

uv tool install "modelscope"

# IndexTTS-2.5
modelscope download --model IndexTeam/IndexTTS-2.5 --local_dir checkpoints

# IndexTTS-2
modelscope download --model IndexTeam/IndexTTS-2 --local_dir checkpoints_2

export HF_ENDPOINT="https://hf-mirror.com"

To diagnose your environment and see which GPUs are detected, use the included utility:

uv run tools/gpu_check.py

# IndexTTS-2.5 (default)
uv run webui.py

# IndexTTS-2
uv run webui.py --version 2 --model_dir ./checkpoints_2

Open your browser and visit http://127.0.0.1:7860 to see the demo.

You can adjust the settings to enable BF16 (IndexTTS-2.5) / FP16 (IndexTTS-2) inference (lower VRAM usage), DeepSpeed acceleration, compiled CUDA kernels for speed, etc. All available options can be seen via:

uv run webui.py -h

For production deployment, see the vLLM recipe for IndexTTS.

To run scripts, use uv run <file.py> so the code runs inside the uv environment. You may also need to add the current directory to PYTHONPATH:

# IndexTTS2.5
PYTHONPATH="$PYTHONPATH:." uv run indextts/infer_v2_5.py \
  --cfg_path checkpoints/config.yaml \
  --model_dir checkpoints \
  --text "Hello world" \
  --lang EN

The default --prompt_wav lives in examples/, which is populated the first time the WebUI starts. To fetch it without the WebUI:

uv run python -c "from indextts.utils.examples_downloader import ensure_examples_available; ensure_examples_available()"

For IndexTTS2, use the Python API below — indextts/infer_v2.py runs a benchmark loop against a hardcoded checkpoints/ directory, not the checkpoints_2 layout from step 3.

# IndexTTS2
from indextts.infer_v2 import IndexTTS2
tts = IndexTTS2(cfg_path="checkpoints_2/config.yaml", model_dir="checkpoints_2", use_fp16=False, use_cuda_kernel=False, use_deepspeed=False)

# IndexTTS2.5
from indextts.infer_v2_5 import IndexTTS2
tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", use_bf16=True)

text = "Translate for me, what is a surprise!"

# IndexTTS2
tts.infer(spk_audio_prompt='examples/voice_01.wav', text=text, output_path="gen.wav", verbose=True)

# IndexTTS2.5 (multilingual, with language selection)
tts.infer(spk_audio_prompt='examples/voice_01.wav', text=text, lang="EN", output_path="gen.wav", verbose=True)

text = "酒楼丧尽天良，开始借机竞拍房间，哎，一群蠢货。"

# IndexTTS2
tts.infer(spk_audio_prompt='examples/voice_07.wav', text=text, output_path="gen.wav", emo_audio_prompt="examples/emo_sad.wav", verbose=True)

# IndexTTS2.5
tts.infer(spk_audio_prompt='examples/voice_07.wav', text=text, lang="ZH", output_path="gen.wav", emo_audio_prompt="examples/emo_sad.wav", verbose=True)

When an emotional reference audio is specified, emo_alpha adjusts how much it affects the output. Valid range: 0.0 - 1.0, default: 1.0 (100%).

text = "酒楼丧尽天良，开始借机竞拍房间，哎，一群蠢货。"

# IndexTTS2
tts.infer(spk_audio_prompt='examples/voice_07.wav', text=text, output_path="gen.wav", emo_audio_prompt="examples/emo_sad.wav", emo_alpha=0.9, verbose=True)

# IndexTTS2.5
tts.infer(spk_audio_prompt='examples/voice_07.wav', text=text, output_path="gen.wav", lang="ZH", emo_audio_prompt="examples/emo_sad.wav", emo_alpha=0.9, verbose=True)

You can omit the emotional reference audio and instead provide an 8-float list specifying the intensity of each emotion, in the order [happy, angry, sad, afraid, disgusted, melancholic, surprised, calm]. Use use_random to introduce stochasticity during inference (default: False).

text = "对不起嘛！我的记性真的不太好，但是和你在一起的事情，我都会努力记住的~"

# IndexTTS2
tts.infer(spk_audio_prompt='examples/voice_09.wav', text=text, output_path="gen.wav", emo_vector=[0, 0, 0.8, 0, 0, 0, 0, 0], use_random=False, verbose=True)

# IndexTTS2.5
tts.infer(spk_audio_prompt='examples/voice_09.wav', text=text, lang="ZH", output_path="gen.wav", emo_vector=[0, 0, 0.8, 0, 0, 0, 0, 0], use_random=False, verbose=True)

Enable use_emo_text to automatically convert your text script into emotion vectors. An emo_alpha around 0.6 (or lower) is recommended for more natural speech. Randomness can be introduced with use_random (default: False).

text = "快躲起来！是他要来了！他要来抓我们了！"

# IndexTTS2
tts.infer(spk_audio_prompt='examples/voice_12.wav', text=text, output_path="gen.wav", emo_alpha=0.6, use_emo_text=True, use_random=False, verbose=True)

# IndexTTS2.5
tts.infer(spk_audio_prompt='examples/voice_12.wav', text=text, lang="ZH", output_path="gen.wav", emo_alpha=0.6, use_emo_text=True, use_random=False, verbose=True)

Provide a specific text emotion description via emo_text, which is converted into emotion vectors — giving you separate control of the text script and the emotion description:

text = "快躲起来！是他要来了！他要来抓我们了！"
emo_text = "你吓死我了！你是鬼吗？"

# IndexTTS2
tts.infer(spk_audio_prompt='examples/voice_12.wav', text=text, output_path="gen.wav", emo_alpha=0.6, use_emo_text=True, emo_text=emo_text, use_random=False, verbose=True)

# IndexTTS2.5
tts.infer(spk_audio_prompt='examples/voice_12.wav', text=text, lang="ZH", output_path="gen.wav", emo_alpha=0.6, use_emo_text=True, emo_text=emo_text, use_random=False, verbose=True)

A value greater than 1.0 slows down the speech, a value less than 1.0 speeds it up. Default: 1.0 (normal speed). Valid range: 0.5 - 2.0.

text = "大家好，欢迎来到IndexTTS的语速控制演示。"

# IndexTTS2.5
# Slow down (1.2x duration)
tts.infer(spk_audio_prompt='examples/voice_01.wav', text=text, lang="ZH", output_path="gen_slow.wav", duration_factor=1.2, verbose=True)

# Speed up (0.8x duration)
tts.infer(spk_audio_prompt='examples/voice_01.wav', text=text, lang="ZH", output_path="gen_fast.wav", duration_factor=0.8, verbose=True)

IndexTTS2.5 — Pinyin / CMU phonemes / Japanese Kana:

IndexTTS2.5 supports these character replacements with better instruction-following capability. For the full list of valid entries, see checkpoints/pinyin.vocab for Pinyin and the CMU dictionary for English phonemes.

他在银<行|XING2>里<行|HANG2>走了半天，发现这笔业务办不<行|HANG2>。

He had a <minute|M IH1 . N AH0 T> to examine the <minute|M AY0 . N UW1 T> details of the contract.

彼は料理が<上手|じょうず>だが、囲碁では<上手|うわて>に負けた。

IndexTTS2 — Pinyin:

IndexTTS2 supports mixed modeling of Chinese characters and Pinyin. To activate Pinyin control, provide text with specific Pinyin annotations. Note that Pinyin control does not work for every possible consonant–vowel combination; only valid Chinese Pinyin cases are supported (see checkpoints/pinyin.vocab).

之前你做DE5很好，所以这一次也DEI3做DE2很好才XING2，如果这次目标完成得不错的话，我们就直接打DI1去银行取钱。

You can also use the previous IndexTTS1 model by importing a different module:

from indextts.infer import IndexTTS
tts = IndexTTS(model_dir="checkpoints", cfg_path="checkpoints/config.yaml")
voice = "examples/voice_07.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, 'gen.wav')

For more details, see README_INDEXTTS_1_5, or visit the IndexTTS1 repository at index-tts:v1.5.0.

Table 1: Zero-shot TTS on CV3-Eval (Arabic uses an in-house test set). †Cited from the original paper.

Table 2: Cross-lingual TTS on CV3-Eval (Chinese prompt → target language, Arabic uses an in-house test set).

RTF (wall-clock time / generated audio duration, lower is faster) on an NVIDIA RTX 4090, kv_cache=True.

• QQ Groups: 663272642 (No.4), 1013410623 (No.5)
• Discord: https://discord.gg/uT32E7KDmy
• Email: indexspeech@bilibili.com

You are welcome to join our community! 🌏 欢迎大家来交流讨论！

For commercial usage and cooperation, please contact indexspeech@bilibili.com.

🌟 If you find our work helpful, please leave us a star and cite our papers.

IndexTTS2.5:

@misc{li2026indextts25technicalreport,
      title={IndexTTS 2.5 Technical Report},
      author={Yunpei Li and Xun Zhou and Jinchao Wang and Lu Wang and Yong Wu and Siyi Zhou and Yiquan Zhou and Yining Wang and Yaogen Yang and Zhetao Hu and Shiyao Duan and Jiacheng Xu and Bin Xia and Jingchen Shu},
      year={2026},
      eprint={2601.03888},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2601.03888},
}

IndexTTS2:

@article{zhou2025indextts2,
  title={IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech},
  author={Siyi Zhou and Yiquan Zhou and Yi He and Xun Zhou and Jinchao Wang and Wei Deng and 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 and Siyi Zhou and Jingchen Shu and Jinchao Wang and Lu Wang},
  journal={arXiv preprint arXiv:2502.05512},
  year={2025},
  doi={10.48550/arXiv.2502.05512},
  url={https://arxiv.org/abs/2502.05512}
}

1. tortoise-tts
2. XTTSv2
3. BigVGAN
4. wenet
5. icefall
6. maskgct
7. seed-vc

This project is released under the bilibili Model Use License Agreement. Please also read the DISCLAIMER before use.