Boson AI
Boson AI
Speech model ·Jun 2026

Higgs Audio v3 TTS

Speech Open (Restricted)
4B
Parameters

About Higgs Audio v3 TTS

Higgs Audio v3 TTS is an AI model developed by Boson AI, in the speech category, released in 2026, made available as an open-weights model with 4B params. A 4B-parameter chat-native autoregressive TTS model built on a Qwen3-4B backbone that streams audio before sentences are.

On this page you'll find Higgs Audio v3 TTS's full specifications. Review provider pricing and benchmark scores below, or compare Higgs Audio v3 TTS head-to-head with other speech models.

Run Higgs Audio v3 TTS locally — what fits

GPUs with enough VRAM to hold Higgs Audio v3 TTS at FP16 (lower precision needs less), from best value to most headroom. Generation speed depends on your tool, resolution and step count, so we don't estimate it.

VRAM fit only — we don't estimate generation speed for image/video/audio models (it depends on the tool, resolution and steps).

Community

Would you run Higgs Audio v3 TTS again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

More models like Higgs Audio v3 TTS

Frequently asked questions

What is Higgs Audio v3 TTS?

A 4B-parameter chat-native autoregressive TTS model built on a Qwen3-4B backbone that streams audio before sentences are It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Higgs Audio v3 TTS?

Higgs Audio v3 TTS was developed by Boson AI and released in 2026.

Is Higgs Audio v3 TTS open source or proprietary?

Higgs Audio v3 TTS ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Higgs Audio v3 TTS cost?

Pricing for Higgs Audio v3 TTS depends on the provider. See the providers table on this page for the latest API rates.

How does Higgs Audio v3 TTS perform on benchmarks?

Benchmark scores for Higgs Audio v3 TTS are listed on this page as they are published. You can compare it head-to-head with other models on the GenAIList compare tool.

Higgs Audio v3 TTS: This Model Does Not Read, It Talks
Higgs Audio v3 TTS: Beyond Reading, Toward Real Speech
SGLang Office Hour 6/11 Higgs Audio V3 TTS
Higgs TTS V3: Natural Speech in 100 Languages
Higgs Audio V3 TTS The AI Voice That Actually Talks Like a Human

Know a great video about Higgs Audio v3 TTS?