Heavy tierTop speech arena score

Breeze TTS 2

BreezeBlue · Breeze

Released August 2026 and currently the #1 open-weight model on the Artificial Analysis speech arena (1,215 Elo). Supports voice cloning from a short reference clip, voice design from a text description, and inline direction tags like (sigh) for emotion. Needs a 12 GB GPU for eager inference or 24 GB for the faster path. Weights are BreezeBlue's Research Non-Commercial license — the code is Apache 2.0, but commercial use requires their paid API.

Params

3B

License

BreezeBlue Research Non-Commercial (code: Apache 2.0)

Min VRAM

12 GB GPU (7.7 GiB eager) / 24 GB GPU (14.4 GiB fast path)

Speed

Time to first audio <40ms · real-time factor 0.32

Languages

English, Chinese

Tier

Heavy

Install & run locally

terminal
git clone https://github.com/breezeblue-ai/breeze-tts.git
cd breeze-tts
python -m pip install -r requirements.txt

python infer.py ../breeze-tts-2 \
  --ref-audio reference_en.wav \
  --ref-text "This is the exact transcript of the English reference audio." \
  --text "(sigh) It is good to hear your voice again after all this time." \
  --output outputs/voice_clone_en.wav

Full install and usage docs on the Hugging Face model card.

Will it run on my hardware?

Breeze TTS 2 needs about 12 GB GPU (7.7 GiB eager) / 24 GB GPU (14.4 GiB fast path) of fast memory. Here is what in our hardware database clears that bar.

Runs at full speed · 12

NVIDIA RTX 5090 32GB32 GB VRAM~$2,999Amazon
NVIDIA RTX 5080 16GB16 GB VRAM~$1,250Amazon
NVIDIA RTX 5070 Ti 16GB16 GB VRAM~$999Amazon
NVIDIA RTX 4060 Ti 16GB16 GB VRAM~$424Amazon
NVIDIA RTX 4070 Super 12GB12 GB VRAM~$734Amazon
NVIDIA RTX 4080 Super 16GB16 GB VRAM~$1,000Amazon
NVIDIA RTX 4090 24GB24 GB VRAM~$2,755Amazon
AMD RX 7900 XTX 24GB24 GB VRAM~$1,339Amazon
Apple Mac mini M4 (16 GB)16 GB unified$799Amazon
Apple Mac mini M4 Pro (24 GB)24 GB unified$1,599Amazon
Apple Mac mini M4 Pro (48 GB)48 GB unified$2,099Amazon
Apple Mac Studio M4 Max (64 GB)64 GB unified$2,899Amazon

Runs, but slower on shared memory · 3

MINISFORUM AI X1 Pro32 GB DDR5 (shared)~$699Amazon
Corsair Vengeance 64 GB DDR5 Kit64 GB DDR5~$1,150Amazon
G.Skill Trident Z5 128 GB DDR5128 GB DDR5~$2,200Amazon

Hardware links are affiliate links. We earn a small commission if you buy through them — at no extra cost to you. Disclosure

Specifications

Parameters3B
LicenseBreezeBlue Research Non-Commercial (code: Apache 2.0)
Min VRAM12 GB GPU (7.7 GiB eager) / 24 GB GPU (14.4 GiB fast path)
SpeedTime to first audio <40ms · real-time factor 0.32
LanguagesEnglish, Chinese
Recommended tierHeavy
Best forvoice cloningvoice designvoice direction

Source

Not distributed through Ollama — install and run it directly from the model card.

View on Hugging Face

Popularity trend (illustrative)

Illustrative adoption trend, not actual download counts. We do not publish a download number for any model because we have no honest source for it.

Similar models