As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/fun-cosyvoice3/

# Fun-CosyVoice3 0.5B (2512) + Fun-ASR-Nano + Fun-Audio-Chat-8B

Alibaba (Tongyi Lab / FunAudioLLM), FunAudioLLM family. Status: current. Type: speech and audio. Released: 2025-12-11.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | `FunAudioLLM/Fun-CosyVoice3-0.5B-2512` |  | https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512 |
| Hugging Face (ASR, 800M) | `FunAudioLLM/Fun-ASR-Nano-2512` |  | https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512 |
| Hugging Face (speech chat, 8B) | `FunAudioLLM/Fun-Audio-Chat-8B` |  | https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B |
| GitHub |  |  | https://github.com/QwenAudio/CosyVoice |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text, audio
- Output: audio
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: apache-2.0

## Where it stands

- Newer speech and audio models in the registry since its release: 74. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Weights are public under a permissive licence (Apache-2.0).

## What stands out

- Small open multilingual zero-shot TTS: 0.5B model with 9 languages (zh, en, ja, ko, de, es, fr, it, ru) and 18+ Chinese dialects/accents; RL variant reports 0.81% CER / 77.4% speaker similarity (zh) and 1.68% WER / 69.5% similarity (en) on its eval set. Source: https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512
- Compact far-field ASR (Fun-ASR-Nano, 800M): zh/en/ja plus 7 Chinese dialect groups and 26 accents; WER 1.80% AIShell1, 1.76% LibriSpeech-clean; tuned for noisy far-field audio and lyrics over music. MLT-Nano variant covers 31 languages. Source: https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512
- Open 8B speech chat model with function calling (Fun-Audio-Chat): Half-duplex speech-to-speech/speech-to-text LLM (zh/en) with dual-resolution speech representations (5 Hz backbone + 25 Hz head, about 50% less compute); spoken QA, speech function calling, voice empathy. Source: https://arxiv.org/abs/2512.20156

## Notes

HF repo creation dates: CosyVoice3-0.5B-2512 2025-12-11, Fun-ASR-Nano-2512 2025-12-15, Fun-Audio-Chat-8B 2025-12-23. CosyVoice3-0.5B had ~197k downloads in the month to 2026-09-29, one of the most-used open TTS checkpoints. Papers: CosyVoice 3 arXiv 2505.17589, FunAudio-ASR arXiv 2509.12508, Fun-Audio-Chat arXiv 2512.20156. GitHub repo moved from FunAudioLLM/CosyVoice to QwenAudio/CosyVoice. The same Tongyi group's hosted successors are the Qwen-Audio 3.x API models.

Alibaba Tongyi's open (Apache-2.0) speech stack from December 2025: TTS, ASR and a speech-chat LLM that you can run locally.

Sources: https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512 · https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512 · https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B · https://arxiv.org/abs/2505.17589

Model page: https://postcutoff.com/m/fun-cosyvoice3/