CosyVoice 3 (Fun-CosyVoice 3.0 & 3.5): What It Is, Demo & How to Use It
CosyVoice 3 is the third generation of the open-source CosyVoice text-to-speech model. Its open release, Fun-CosyVoice 3.0 (December 2025), clones a voice from a short sample in 9 languages and 18+ Chinese dialects. CosyVoice 3.5 is a newer model offered through Alibaba Cloud's API, with no open weights published.
CosyVoice versions: 1, 2, 3, Fun-CosyVoice 3.0 and 3.5
Which versions you can download, and which exist only as a paper or a hosted API.
| Version | Model | Open weights | Date | Source |
|---|---|---|---|---|
| CosyVoice 1 | CosyVoice-300M (plus -SFT and -Instruct) | Yes | Jul 2024 (paper) | arXiv |
| CosyVoice 2 | CosyVoice2-0.5B | Yes | Dec 2024 | README |
| CosyVoice 3 (paper) | Research models up to 1.5B parameters | No — the 1.5B model is paper only | May 2025 (paper) | arXiv |
| Fun-CosyVoice 3.0 | Fun-CosyVoice3-0.5B-2512 (base and RL) | Yes | Dec 2025 | README |
| CosyVoice 3.5 | cosyvoice-v3.5-flash, cosyvoice-v3.5-plus | No — Alibaba Cloud API only | Not stated | Alibaba Cloud |
What's new in CosyVoice 3 vs CosyVoice 2
The CosyVoice 3 paper aims at "in-the-wild" speech: natural, speaker-consistent audio across languages and recording conditions, not only clean studio data.
A multi-task speech tokenizer
A new speech tokenizer trained on five supervised tasks — speech recognition, emotion recognition, language identification, audio event detection and speaker analysis — to make prosody more natural.
Reward-model post-training
A differentiable reward model is used for post-training; the paper notes it also applies to other LLM-based speech models.
100× more training data
Training data grows from 10,000 to 1,000,000 hours, covering 9 languages and 18 Chinese dialects.
A bigger model in the paper
Parameters grow from 0.5B to 1.5B in the paper. The open Fun-CosyVoice 3.0 checkpoint is 0.5B.
Pronunciation control and text normalization
Correct a pronunciation with Chinese Pinyin or English CMU phonemes, and read numbers and symbols without a separate text front-end.
Bi-streaming and instructions
Text-in and audio-out streaming with latency as low as 150 ms, plus instructions for language, dialect, emotion, speed and volume.
Languages and Chinese dialects
The open Fun-CosyVoice 3.0 model covers 9 languages and 18+ Chinese dialects and accents, and clones voices across languages — for example, English speech in a voice recorded in Chinese.
- 9 languages
- Chinese, English, Japanese, Korean, German, Spanish, French, Italian, Russian
- 18+ Chinese dialects and accents, including
- Guangdong (Cantonese), Minnan, Sichuan, Dongbei, Shaanxi, Shanxi, Shanghai, Tianjin, Shandong, Ningxia, Gansu
Hugging Face: Fun-CosyVoice3-0.5B-2512
Hear dialect voices on our Cantonese & Dialects page, and mixed-language speech on the Multilingual TTS page.
Zero-shot voice cloning
Zero-shot means CosyVoice 3 copies a voice from a short reference recording at generation time, with no training per speaker. The official README lists multi-lingual and cross-lingual zero-shot cloning among its key features.
On CosyVoice.org, voice cloning runs on hosted CosyVoice 3-generation models: upload a sample you have permission to use and generate speech in your browser. Clone a voice
Open-source weights vs hosted models
There are two ways to use CosyVoice 3: download the open weights and run them yourself, or call Alibaba Cloud's hosted models through Model Studio (DashScope).
| Compare | Open weights (Fun-CosyVoice 3.0) | Hosted (Alibaba Cloud Model Studio) |
|---|---|---|
| Models | Fun-CosyVoice3-0.5B-2512 and its RL variant | cosyvoice-v3-flash, cosyvoice-v3-plus, cosyvoice-v3.5-flash, cosyvoice-v3.5-plus |
| Where | GitHub, Hugging Face, ModelScope | Model Studio WebSocket API and the DashScope Python/Java SDKs |
| Regions | Wherever you run it | v3: Singapore and China (Beijing). v3.5: China (Beijing) only |
| Cost | Free to download (Apache-2.0); you pay for your own GPU | Billed per input character |
| Setup | Python 3.10 environment, model download, your own GPU server | An API key — no GPU |
Download the open weights:QwenAudio/CosyVoice READMEHugging Face: Fun-CosyVoice3-0.5B-2512ModelScope: Fun-CosyVoice3-0.5B-2512
Model differences, official prices and a quick start for the hosted API are in our CosyVoice API guide.
Try CosyVoice 3 without installing anything
Type a line in the free online tool, or listen to the official demo sentences compared across CosyVoice 2.0, CosyVoice 3.0-0.5B and CosyVoice 3.0-1.5B.
CosyVoice 3 FAQ
What is the difference between CosyVoice 3.0 and CosyVoice 3.5?
CosyVoice 3.0 is the open release, Fun-CosyVoice3-0.5B-2512, which you can download and run yourself. CosyVoice 3.5 is a hosted model family (cosyvoice-v3.5-flash and cosyvoice-v3.5-plus) on Alibaba Cloud Model Studio, listed for the China (Beijing) region; Alibaba's docs list voice cloning, voice design and instruction control for both. As of October 2026 there are no CosyVoice 3.5 weights in the official GitHub, Hugging Face or ModelScope repositories.
Is CosyVoice 3 open source?
Yes. Fun-CosyVoice 3.0 (Fun-CosyVoice3-0.5B-2512) is published with its training and inference scripts under the Apache-2.0 license. The 1.5B model described in the CosyVoice 3 paper has not been released as open weights.
Is cosyvoice3 the same as CosyVoice 3?
Yes. cosyvoice3, CosyVoice 3.0 and Fun-CosyVoice 3.0 all refer to the third generation; Fun-CosyVoice 3.0 is the name the official repository uses for the open release.
Can I use CosyVoice 3 commercially?
The open model is released under Apache-2.0, but the README also says its content is for academic and demonstration purposes — read both and get your own legal advice. On CosyVoice.org, commercial use is included in the Pro plan.
How much GPU memory does CosyVoice 3 need?
The official README and model card don't state a minimum GPU or VRAM requirement, so test on your own hardware. If you'd rather not run a GPU, use the hosted version on this site or Alibaba Cloud Model Studio.
How many languages does CosyVoice 3 support?
9 languages — Chinese, English, Japanese, Korean, German, Spanish, French, Italian and Russian — plus 18+ Chinese dialects and accents, according to the official model card.
Sources
Facts on this page were checked against these official sources on October 26, 2026.