LLM Reference
Boson AI API

Using Higgs Audio v3 TTS on Boson AI API

Implementation guide · Higgs Audio · Boson AI

ServerlessOpen Weights

Boson AI API exposes Higgs Audio v3 TTS through model ID higgs-audio-v3-tts. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-29. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Boson AI API and generate an API key.
  2. 2
    Use the Boson AI API SDK or REST API to call higgs-audio-v3-tts — see the documentation for request format.
API PortalDocumentationModel Card

Code Examples

See Boson AI API documentation for integration details.

Pricing on Boson AI API

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.

Full model details →

Model Specs

Released2026-06-04
Parameters4B
Context8k
ArchitectureDecoder Only

Provider

Boson AI API
Boson AI API

Boson AI