# Bilibili's IndexTTS-2.5 Refines Zero-Shot Voice Cloning

> The latest text-to-speech model from bilibili's Index team pairs voice cloning with emotion control across Chinese, English, and Japanese.

Published by The Open Weights on Aug 10, 2026. Canonical: https://theopenweights.com/news/indextts-2-5-s7an

## Key facts

- Company: IndexTeam
- Model: IndexTTS-2.5
- Version: 2.5
- Category: Text → Speech
- Modalities: Text → Speech
- License: Other (Open weights, commercial use allowed)
- Languages: zh, en, ja
- Significance: notable
- Published: 2026-08-10
- Last verified: 2026-08-23
- Hugging Face: https://huggingface.co/IndexTeam/IndexTTS-2.5
- Canonical URL: https://theopenweights.com/news/indextts-2-5-s7an

Bilibili's Index team has published [IndexTTS-2.5](https://huggingface.co/IndexTeam/IndexTTS-2.5), the newest iteration of its text-to-speech system on Hugging Face. The model targets zero-shot voice cloning, meaning it can reproduce a speaker's voice from a short reference sample without task-specific fine-tuning.

Beyond straightforward cloning, IndexTTS-2.5 offers emotion control and cross-lingual synthesis. According to the release, it supports Chinese, English, and Japanese, positioning it for use cases that span dubbing, localization, and expressive narration.

## Why it matters

Zero-shot cloning with emotion steering has become a competitive frontier in open speech models, and multilingual coverage is what separates a demo from a production tool. A few practical implications:

- Creators can generate voiceovers in three major languages from a single reference clip.
- Emotion control gives finer editorial command over tone without re-recording.
- Coming from bilibili, a large video platform, the model reflects real content-production demands.

The model ships under a custom license, so teams evaluating it for commercial work should review the terms on the [model page](https://huggingface.co/IndexTeam/IndexTTS-2.5) before deploying. As a point release in the IndexTTS line, version 2.5 signals steady, incremental progress rather than a ground-up redesign.

## Get the model

- [Hugging Face](https://huggingface.co/IndexTeam/IndexTTS-2.5)

## Sources

- [IndexTeam/IndexTTS-2.5](https://huggingface.co/IndexTeam/IndexTTS-2.5) — Hugging Face, Aug 10, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Bilibili's IndexTTS-2.5 Refines Zero-Shot Voice Cloning", The Open Weights, Aug 10, 2026, https://theopenweights.com/news/indextts-2-5-s7an