As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/higgs-audio-v3/

# Boson AI Higgs Audio v3 (Higgs TTS 3 4B / Higgs STT 3)

Boson AI, Higgs Audio family. Status: current. Type: speech and audio. Released: 2026-06-04.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | `bosonai/higgs-audio-v3-tts-4b` |  | https://huggingface.co/bosonai/higgs-audio-v3-tts-4b |
| GitHub |  |  | https://github.com/boson-ai/higgs-audio |
| SGLang-Omni |  |  | https://www.lmsys.org/blog/2026-06-04-higgs-audio-v3-tts/ |

## Pricing

- Price not published.
- Last checked: 2026-09-29

## Specs

- Input: text, audio
- Output: audio, text
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: Boson Higgs TTS 3 Research and Non-Commercial License (TTS weights; Creator Use Grant for attributed monetized content)

## Where it stands

- Newer speech and audio models in the registry since its release: 53. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Weights are public. Licence: Boson Higgs TTS 3 Research and Non-Commercial License. See the licence for commercial terms.

## What stands out

- 102-language expressive TTS with zero-shot cloning: ~4B AR decoder (24 kHz, 8 codebooks); 85 languages at production quality (WER/CER <5%), 17 usable; inline control of emotion, style, prosody, pauses and sound effects; 8K-token context; sub-second TTFA streaming. Source: https://huggingface.co/bosonai/higgs-audio-v3-tts-4b
- Higgs STT 3 (API): Speech-to-text model (2026-03-18) for 94 languages; 1.55% WER on LibriSpeech test-clean vs 2.10% for Whisper-large-v3 (company figures). No open weights found. Source: https://www.boson.ai/blog/higgs-audio-v3-stt

## Notes

TTS weights non-commercial; production/hosted use needs a Boson commercial license or the Boson API (pricing not found). Also mirrored as bosonai/higgs-tts-3-4b. Predecessor Higgs Audio v2 (2025, Apache-2.0-style) on the same GitHub.

Sources: https://huggingface.co/bosonai/higgs-audio-v3-tts-4b , https://www.boson.ai/blog/higgs-audio-v3-tts , https://www.boson.ai/blog/higgs-audio-v3-stt

Model page: https://postcutoff.com/m/higgs-audio-v3/