{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/fun-cosyvoice3/","md":"https://postcutoff.com/m/fun-cosyvoice3/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"fun-cosyvoice3","name":"Fun-CosyVoice3 0.5B (2512) + Fun-ASR-Nano + Fun-Audio-Chat-8B","org":"Alibaba (Tongyi Lab / FunAudioLLM)","family":"FunAudioLLM","released":"2025-12-11","status":"current","type":"audio/speech","modality_in":["text","audio"],"modality_out":["audio"],"open_weights":true,"model_license":"apache-2.0","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Hugging Face","model_id":"FunAudioLLM/Fun-CosyVoice3-0.5B-2512","url":"https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512"},{"provider":"Hugging Face (ASR, 800M)","model_id":"FunAudioLLM/Fun-ASR-Nano-2512","url":"https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512"},{"provider":"Hugging Face (speech chat, 8B)","model_id":"FunAudioLLM/Fun-Audio-Chat-8B","url":"https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B"},{"provider":"GitHub","url":"https://github.com/QwenAudio/CosyVoice"}],"capabilities":[{"name":"Small open multilingual zero-shot TTS","detail":"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.","first":false,"discovered":"launch","source":"https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512"},{"name":"Compact far-field ASR (Fun-ASR-Nano, 800M)","detail":"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.","first":false,"discovered":"launch","source":"https://huggingface.co/FunAudioLLM/Fun-ASR-Nano-2512"},{"name":"Open 8B speech chat model with function calling (Fun-Audio-Chat)","detail":"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.","first":false,"discovered":"launch","source":"https://arxiv.org/abs/2512.20156"}],"entry":null,"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.","verified":"2026-09-29","body_md":"Alibaba Tongyi's open (Apache-2.0) speech stack from December 2025: TTS, ASR and a speech-chat LLM that you can run locally.\n\nSources: 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","page_url":"https://postcutoff.com/m/fun-cosyvoice3/","standing":{"kind":"speech and audio","newer_count":74,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":null,"after":null,"weights":"public","licence":"apache-2.0","licence_permissive":true,"summary":"Weights are public under a permissive licence (Apache-2.0)."}}