Model reference · open weights
higgs-audio-tts-transformers is an open-weight audio or speech model from multimodalart, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Higgs Audio v3 TTS (4B) — transformers trustremotecode port A trustremotecode packaging of bosonai/higgs-audio-v3-tts-4b that loads with plain 🤗 transformers (no SGLang). The weights are the original checkpoint, copied unchanged; only a small modeling.py / configuration.py pair and an automap were added. The model is a standard Qwen3-4B backbone plus a fused multi-codebook audio embedding/head. Reference-audio encoding and waveform decoding use the transformers-native bosonai/higgs-audio-v2-tokenizer (higgsaudiov2tokenizer), loaded automatically on first use. Requires transformers = 5.5. Usage generatespeech returns a mono 24 kHz waveform as a CPU float32 tensor [L]. Notes - Generation uses Higgs' delay pattern across 8 codebooks (vocab 1026, incl. BOC/EOC specials); de-delay + decode are handled internally. - The codec runs in fp32 (decode is unstable in bf16); the LM backbone runs in the dtype you load it in (bf16 recommended). - License: research/non-commercial, inherited from the upstream checkpoint — see LICENSE.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | multimodalart |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 4.7B |
| Variants | 1 |
| Runs with | transformers |
| Based on | bosonai/higgs-audio-v3-tts-4b |
| Released | 2026-06-05 |
| Popularity | 44k downloads / month |
| Likes | 20 |
| Licence | Commercial licence needed |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| higgs-audio-v3-tts-4b-transformers | 4.7B | BF16 | ~10.7 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys higgs-audio-tts-transformers for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (higgs-audio-tts-transformers below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="higgs-audio-tts-transformers" -F file=@audio.mp3
Details
Languages
Tags
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗