Last refreshed 2026-10-08. Next refresh: weekly.
Why use Higgs Audio v3 TTS on Boson AI API?
Boson AI API offers Higgs Audio v3 TTS. Boson AI's hosted API for Higgs Audio TTS and STT models.
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: higgs-audio-v3-ttsModel ID
higgs-audio-v3-ttsRequest example
Curated snippets for this provider are not sourced yet. Use Boson AI API documentation with model ID
higgs-audio-v3-tts.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Capabilities
Audio
About Higgs Audio v3 TTS
Higgs Audio v3 TTS is Boson AI's 4B-parameter text-to-speech model released June 4, 2026. It supports 102 languages (85 at production quality with WER/CER <5%), zero-shot voice cloning, and inline control tokens for emotion (21 types), style (singing/shouting/whispering), sound effects, and prosody. Audio output is 24kHz MP3 or PCM. Open weights available under a non-commercial license; hosted API is in free public preview.
Get Started
Model Specs
Released2026-06-04
Parameters4B
Context8K
ArchitectureDecoder Only