All tasks / Models
Breeze TTS 2
BreezeBlue's open-weights English and Chinese text-to-speech model with voice cloning, voice design and streaming.
- BreezeBlue
- Open weights
- Released 25 Aug 2026
Where it ranks
- BText to speechModels · Local · 1,222 on Artificial Analysis Speech Arena: Text to Speech (provider voices)
Facts
- Vendor
- BreezeBlue
- Family
- Breeze TTS
- Released
- 25 Aug 2026
- Weights
- Open: download and run it yourself
- License
- BreezeBlue Research and Non-Commercial License (weights); inference code Apache-2.0
- Parameters
- 3.47B
- GPU memory to run locally
- ~12 GB (Model card: about 7.7 GiB of GPU memory for eager inference, 12 GB GPU recommended minimum (24 GB for the fast path).)
- API price
- $34 per 1M characters (Artificial Analysis normalised price for Breeze TTS 2 (USD per 1M characters).)
- Access
- Free (open weights)
- Last verified
- 18 Oct 2026
Price from artificialanalysis.ai, 18 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Speech Arena: Text to Speech (provider voices) | 1,222 | Breeze TTS 2Provider Voice Arena, all categories and accents; rank 11 of 96, 2138 appearances, 95% CI ±14; raw value from the page's embedded data (shown rounded); no last-updated date shown, so as_of = retrieval date. | 18 Oct 2026 | artificialanalysis.ai |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.