index-tts
A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
GraphCanon updated 3w · GitHub synced 3w · 27 views this month
Decision brief
IndexTTS is an industrial-level controllable zero-shot text-to-speech system that excels in duration control and emotionally expressive speech generation using autoregressive models.
Good fit when
- Use IndexTTS when precise speech duration control is required, such as for professional video dubbing projects where audio-visual synchronization needs to be exact.
- Choose it for applications needing independent adjustment of timbre and emotional tone without the need for extensive customization per speaker or emotion.
Avoid when
- Avoid using IndexTTS in scenarios where minimal latency is critical, as its autoregressive generation mode may introduce processing delays compared to non-autoregressive methods.
- Do not use if you require support for a wide variety of languages beyond what the system's zero-shot capabilities cover.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Active (14d since push)
- As of 3w
- Provenance
- Not a fork · Personal account
- As of 3w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install index-ttsSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
IndexTTS2 proposes a novel method for controlling the duration of synthesized speech in autoregressive models, enhancing their flexibility and usability in applications like video dubbing.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Jul 29, 2026
- Languages
- python
Source: github.language+pyproject.toml · Jul 29, 2026
Categories
Tags
README
The repository history has been reset. Please delete your local copy and re-clone.
（仓库历史已重置。请删除本地副本并重新克隆。）
👉🏻 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 the authors for more detailed information. For commercial usage and cooperation, please contact indexspeech@bilibili.com.
Feel IndexTTS2
IndexTTS2: The Future of Voice, Now Generating
Click the image to watch the IndexTTS2 introduction video.
Contact
QQ Group：663272642(No.4) 1013410623(No.5)
Discord：https://discord.gg/uT32E7KDmy
Email：indexspeech@bilibili.com
You are welcome to join our community
For agents
This page has a .md twin and JSON over the API.