bosonai/higgs-tts-3-4b
text-to-speech model by bosonai
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Higgs TTS 3 is built for voice chat: it speaks, not just reads. It turns model responses into expressive conversational speech across 100+ languages, with zero-shot voice cloning and inline control over emotion, style, prosody, pauses, and sound effects. Higgs autoregressive decoder consumes interleaved text and audio tokens. Audio is encoded by the Higgs Tokenizer into 8 codebooks at 25 fps, staggered via a delay pattern, then mapped to backbone hidden states through a multi-codebook fused embedding. Output codes pass through a multi-codebook fused head, are de-delayed, and decoded back to waveform. The model reaches single-digit WER/CER on 102 languages, which split into two tiers. 🇿🇦 Afrikaans · 🇸🇦🇪🇬 Arabic · 🇦🇲 Armenian · 🇮🇳 Assamese · 🇪🇸 Asturian · 🇦🇿 Azerbaijani · 🇷🇺 Bashkir · 🇪🇸 Basque · 🇧🇾 Belarusian · 🇧🇩🇮🇳 Bengali · 🇧🇦 Bosnian · 🇧🇬 Bulgarian · 🇪🇸 Catalan · 🇵🇭 Cebuano · 🇮🇶 Central Kurdish…
Read the full model card ↗ · Preview checked 2026-10-28T02:03:48.287Z
Inside the original model card — Document outline
- Higgs TTS 3
- Supported Languages
- WER/CER under 5 — polished, production-quality (85)
- WER/CER between 5 and 10 — usable, but less polished (17)
- Control Tokens
- Evaluation Benchmarks
- Multilingual Voice Clone
- Emergent TTS
- Usage
- SGLang Usage
- Install and Serve
- Zero-shot synthesis
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
bosonai/higgs-tts-3-4b is a text-to-speech model repository published by bosonai on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- transformers
- Recent downloads (30 days)
- 124,515
- Cumulative likes
- 826
- Hugging Face trending score
- 7
- Reported safetensors parameters
- 4,654,850,537
- Architecture
- HiggsMultimodalQwen3ForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-06-04T05:37:32.000Z
- Last modified
- 2026-09-04T00:12:39.000Z
Compatibility and lineage
Reported languages: af, ar, as, ast, az, ba, be, bg, bn, bs, ca, ceb, ckb, cs, cy, da, de, el, en, eo, es, et, eu, fa, fi, fr, ga, gl, gu, ha, he, hi, hr, ht, hu, hy, id, is, it, jv
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:52:33.137Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.