IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech

TL;DR

IndexTTS2 introduces a novel autoregressive TTS model that enables precise duration control, emotional expression disentanglement, and zero-shot speaker adaptation, significantly advancing speech naturalness and synchronization capabilities.

Contribution

The paper presents IndexTTS2, a new autoregressive TTS framework supporting explicit duration control, emotional and speaker disentanglement, and a soft instruction mechanism for improved zero-shot emotional speech synthesis.

Findings

Outperforms state-of-the-art zero-shot TTS models in key metrics.

Supports precise speech duration control in autoregressive generation.

Effectively disentangles emotion and speaker identity for flexible synthesis.

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: https://index-tts.github.io/index-tts2.github.io/