All models
flagship

Higgs Audio v2

Boson Higgs Audio 2 Community License (weights; conditional commercial use)

Built on Llama 3.2 3B, 10M+ hours of training audio

Higgs Audio v2 is now published as Higgs TTS 2. Its model weights use the Boson Higgs Audio 2 Community License, which incorporates Meta Llama terms; they are not Apache-2.0. The agreement includes attribution and use conditions, plus a separate-license requirement above 100,000 annual active users. Review the exact checkpoint license before using it in a commercial service. OpenSpeech has not independently established a quality ranking for this model.

Hear Higgs Audio v2

Higgs Audio v2 · Default · Same three scripts across the directory.

Run it yourself

Best for: Built on Llama 3.2 3B, 10M+ hours of training audio

Commercial conditions: Weight agreement includes attribution, incorporated Llama terms, use restrictions and a separate-license requirement above 100,000 annual active users.

Code: See repository license. Weights: Boson Higgs Audio 2 Community License. License sources checked 2026-09-20. Source 1

Before you choose: Custom weight license with conditions for hosted services. License label checked September 19, 2026; remaining performance, language and historical sample details still require a full review.

Details awaiting a fresh review. Hardware figures are estimates unless a benchmark is linked.

Compare with similar

Compare all →
Fish Speech 1.5Listen side-by-side →Qwen3-TTSListen side-by-side →ChatterboxListen side-by-side →

Choose an alternative to hear both models together.

Voices

1 voice
Neutral
Defaultdefault
—

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Run Higgs Audio v2

pip install higgs-audio

Sources & setup details

Higgs Audio v2 FAQ

Do I need a GPU to run Higgs Audio v2?

The directory lists roughly 12 GB of VRAM as a historical estimate. Check the model documentation for your checkpoint and runtime.

Can Higgs Audio v2 clone voices?

Yes — Higgs Audio v2 supports voice cloning from reference audio.

What license is Higgs Audio v2 released under?

Higgs Audio v2 is released under the Boson Higgs Audio 2 Community License (weights; conditional commercial use) license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does Higgs Audio v2 support?

Higgs Audio v2 supports English, Chinese, Spanish, French, German, Japanese, Korean.

Is there a hosted Higgs Audio v2 API?

OpenSpeech Cloud is accepting production-access interest for Higgs Audio v2, but this model is not currently hosted in Cloud. Use the official repository for current deployment options.