# Alibaba Releases CosyVoice 3 for Expressive TTS

> The new 500-million-parameter text-to-speech model from the Qwen team offers multilingual voice cloning and emotional control.

Published by The Open Weights on Dec 11, 2025. Canonical: https://theopenweights.com/news/fun-cosyvoice3-0-5b-ee4a

## Key facts

- Company: Qwen · Alibaba
- Model: Fun-CosyVoice3-0.5B
- Version: 3
- Category: Text → Speech
- Modalities: Text → Speech
- License: Other (Open weights, commercial use allowed)
- Parameters: 500M
- Languages: 9 languages
- Significance: notable
- Published: 2025-12-11
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512
- Canonical URL: https://theopenweights.com/news/fun-cosyvoice3-0-5b-ee4a

Alibaba’s FunAudioLLM team, part of the group behind the Qwen model family, has released Fun-CosyVoice3, a 500-million-parameter foundation model for text-to-speech (TTS). The model is designed to generate highly natural, expressive, and controllable human-like speech, pushing the boundaries of open generative audio.

CosyVoice 3 stands out for its rich feature set, which brings it closer to capabilities offered by leading proprietary services. It provides a robust tool for developers working on sophisticated voice applications.

## Cloning, Control, and Multilingual Support

The model's core strengths lie in its versatility and fine-grained control. Key features highlighted in the [official release](https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512) include:

*   **Multilingual and Accent Support:** CosyVoice 3 handles over ten languages, including English, Chinese, Japanese, French, and Spanish, and can manage code-switching between them.
*   **Zero-Shot Voice Cloning:** It can replicate a speaker’s voice from a mere 3-second audio clip, even performing cross-lingual cloning where the target language differs from the source clip.
*   **Expressive Control:** The model allows for adjustments to emotion, style, rhythm, and prosody, enabling the generation of nuanced and context-aware speech.

While the model is available for commercial use, it is released under the `tongyi-qianwen-license-1.0`, which carries restrictions. Companies with more than 100 million monthly active users must seek a separate license from Alibaba, a detail developers should note before integrating it into large-scale products.

## Get the model

- [Hugging Face](https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512)

## Sources

- [FunAudioLLM/Fun-CosyVoice3-0.5B-2512](https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512) — Hugging Face, Dec 11, 2025

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Alibaba Releases CosyVoice 3 for Expressive TTS", The Open Weights, Dec 11, 2025, https://theopenweights.com/news/fun-cosyvoice3-0-5b-ee4a