whatmodel.sh / tts / Breeze TTS 2
Breeze TTS 2
↗ share
+ contribute
Breeze TTS 2 is an open-weights text-to-speech model from BreezeBlue, released August 2026. Its published size is 3.47B parameters. Licence: breezeblue-research-nc.
$ how it compares
Scored text-to-speech models released closest to Breeze TTS 2, out of 148 with a score.
| # | model | score | where |
|---|---|---|---|
| 7 | 69±2 | api $20.00/M chars | |
| 12 | 67±3 | local | |
| 13 | 67±3 | api $6.00/M chars | |
| 29 | 64±4 | local | |
| 48 | 61±2 | api $25.00/M chars |
see all text-to-speech models · find the ones that fit your machine
$ where to run it
Through an API
api · $28.00/M chars · breezeblue.ai ↗ · price sourceUSD per 1M characters: BreezeBlue lists $28 / 1M characters on the Pro plan ($99/month; lowest published self-serve rate), $32 Creator, $36 Starter, $40 Free top-up. Docs: TTS metered per character, 10 billable units = 1 credit, credits shared by Studio and API; CJK characters count as two units. Product: Breeze Developer API. API model: breeze-tts-2. Settings: Pro-plan rate, non-CJK text. Price basis: published list rate. Exclusions: monthly plan fee, voice design/clone fees. Currency: USD. BreezeBlue official pricing page and docs, observed 2026-09-25.
Other ways to run it
version
- Run it as published · needs ~8.83 GB, NVIDIA only · from huggingface.co/BreezeBlue (official)
git clone https://github.com/breezeblue-ai/breeze-tts.git && cd breeze-tts && python -m pip install -r requirements.txt && hf download BreezeBlue/Breeze-TTS-2 --local-dir ../breeze-tts-2 && python infer.py ../breeze-tts-2 --ref-audio ref.wav --ref-text 'Transcript of ref.wav' --text 'Hello world' --output out.wav
Official weights and documentation: huggingface.co/BreezeBlue ↗
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json