Free, rate-limited public preview. Get a key at boson.ai/workspace.

export BOSON_API_KEY=bai-xxxx

curl https://api.boson.ai/v1/audio/speech \
  -H "Authorization: Bearer $BOSON_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "higgs-audio-v3-tts", "input": "Hello, this is a test."}' \
  --output out.mp3

OpenAI-compatible; supports preset voices, zero-shot cloning, and streaming. Full reference: API docs.

Weights: bosonai/higgs-audio-v3-tts-4b. We recommend serving with SGLang-Omni:

export HF_TOKEN=hf_xxxxxxxxxxxxxxxx
hf download bosonai/higgs-audio-v3-tts-4b

sgl-omni serve --model-path bosonai/higgs-audio-v3-tts-4b --port 8000

Serving, voice-cloning, and streaming recipes are in the model card and the SGLang-Omni cookbook.

The full v2 / v2.5 documentation — installation, examples, technical details, and benchmarks — has moved to README_V2.md. Those models remain available on Hugging Face: v2 (3B base) and the v2.5 blog.

For contribution and support guidelines, please see SUPPORT_GUIDELINES.md.

If you are passionate about multimodal AI, speech/audio models, or large-scale systems, check out our open positions at Boson AI Careers.

@misc{bosonai_higgs_audio_tts_v3_2026,
  title  = {Higgs Audio v3 TTS: Conversational Speech for Voice AI from Boson AI},
  author = {Boson AI},
  year   = {2026},
  howpublished = {https://huggingface.co/bosonai/higgs-audio-v3-tts-4b},
}

The boson_multimodal/audio_processing/ directory contains code derived from third-party repositories, primarily from xcodec. See the LICENSE in that directory for attribution and licensing.