BreezeBlue/Breeze-TTS-2 — new model trending #19 on Hugging Face
BreezeBlue open-weights Breeze TTS 2, a bilingual text-to-speech model it ranks #1 among open-weight models on the Artificial Analysis TTS leaderboard.
BreezeBlue released open weights and Apache 2.0-licensed PyTorch inference code for Breeze TTS 2 on 2026-08-25. The text-to-speech model supports English and Chinese, voice cloning, reference-free voice design, voice direction, and inline vocal events like (laugh) and (sigh). Reported performance includes #1 open-weight ranking on the Artificial Analysis Elo leaderboard, under 40 ms time-to-first-audio, a 0.32 real-time factor on an NVIDIA H100, and about 7.7 GiB GPU memory for eager inference.
- Open weights and inference code released; weights limited to research and non-commercial use
- Claims #1 among open-weight TTS models on Artificial Analysis leaderboard, outperforming proprietary systems
- Bilingual English-Chinese generation with voice clone, design, direction, and inline vocal events
- Under 40 ms time-to-first-audio and 0.32 RTF streaming on an NVIDIA H100 fast path
- Requires roughly 7.7 GiB GPU memory for eager inference; 12 GB GPU minimum recommended
- Vendors
- BreezeBlue
- Products
- Breeze TTS 2
- Organizations
- Hugging FaceArtificial Analysis
- AI models
- Breeze-TTS-2
From the original article
5 min read at huggingface.cotext-to-speech · 7,243 downloads · 481 likes · license other
By BreezeBlue · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.