{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/breeze-tts-2/","md":"https://postcutoff.com/m/breeze-tts-2/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":"breeze-tts-2","name":"Breeze TTS 2","org":"BreezeBlue","family":"Breeze TTS","released":"2026-08-25","status":"current","type":"audio/speech","modality_in":["text","audio"],"modality_out":["audio"],"open_weights":true,"model_license":"BreezeBlue Research and Non-Commercial License (weights); Apache-2.0 (code)","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":null,"price_line":"Price not published","access":[{"provider":"Hugging Face","model_id":"BreezeBlue/Breeze-TTS-2","url":"https://huggingface.co/BreezeBlue/Breeze-TTS-2"},{"provider":"GitHub","url":"https://github.com/breezeblue-ai/breeze-tts"},{"provider":"BreezeBlue (hosted / commercial license)","url":"https://breezeblue.ai"}],"capabilities":[{"name":"#1 open-weights TTS on Artificial Analysis","detail":"~1,206-1,215 Elo in the Artificial Analysis Speech Arena, ~90 points above Fish Audio S2 Pro, #6 overall at launch — the leading open-weights TTS as of Sept 2026.","first":false,"discovered":"later","source":"https://x.com/ArtificialAnlys/status/2092399623839326550"},{"name":"Clone + design + direct in one 3B checkpoint, <40 ms TTFA","detail":"Voice cloning from reference audio, voice design from text descriptions, voice direction (tone/emotion keeping identity), vocal events (laughs, coughs); streaming TTFA under 40 ms on H100 with fast path, RTF 0.32.","first":false,"discovered":"launch","source":"https://huggingface.co/BreezeBlue/Breeze-TTS-2"}],"entry":"2026-08-25-breeze-tts-2","notes":"Model card lists English + Chinese; the Artificial Analysis post mentions 50 languages (possibly the hosted model) — unresolved. Needs 12 GB VRAM (24 GB recommended), CUDA/Linux. Weights are NOT commercially usable without a BreezeBlue subscription. Some secondary blogs claim it is the 'first open-weight model to beat ElevenLabs' flagship' — unverified and contradicted by the AA leaderboard (Eleven v4 far ahead).","verified":"2026-09-29","body_md":"Sources: https://huggingface.co/BreezeBlue/Breeze-TTS-2 , https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice/open-weights","page_url":"https://postcutoff.com/m/breeze-tts-2/","standing":{"kind":"speech and audio","newer_count":33,"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":"BreezeBlue Research and Non-Commercial License (weights); Apache-2.0 (code)","licence_permissive":false,"summary":"Weights are public. Licence: BreezeBlue Research and Non-Commercial License; Apache-2.0. See the licence for commercial terms."}}