bosonai/higgs-tts-2-3b-base
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.
Check our open-source repository https://github.com/boson-ai/higgs-audio for more details! We are open-sourcing Higgs TTS 2, a powerful audio foundation model pretrained on over 10 million hours of audio data and a diverse set of text data. Despite having no post-training or fine-tuning, Higgs TTS 2 excels in expressive audio generation, thanks to its deep language and acoustic understanding. On EmergentTTS-Eval, the model achieves win rates of 75.7% and 55.7% over "gpt-4o-mini-tts" on the "Emotions" and "Questions" categories, respectively. It also obtains state-of-the-art performance on traditional TTS benchmarks like Seed-TTS Eval and Emotional Speech Dataset (ESD). Moreover, the model demonstrates capabilities rarely seen in previous systems, including automatic prosody adaptation during narration, zero-shot generation of natural multi-speaker dialogues in multiple languages, melodic humming with the cloned voice, and simultaneous generation of speech and background music. Here's the demo video that shows some of its emergent capabilities (remember to unmute): Here's another demo…
Read the full model card ↗ · Preview checked 2026-10-31T16:45:29.198Z
Inside the original model card — Document outline
- Higgs TTS 2: Redefining Expressiveness in Audio Generation
- Technical Details
- Audio Tokenizer
- Model Architecture -- Dual FFN
- Evaluation
- Seed-TTS Eval & ESD
- EmergentTTS-Eval ("Emotions" and "Questions")
- Multi-speaker Eval
- Usage
- Transformers 🤗
- Original codebase
- License
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-2-3b-base 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)
- 17,562
- Cumulative likes
- 693
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 5,771,283,456
- Architecture
- HiggsAudioV2ForConditionalGeneration
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2025-07-01T15:45:49.000Z
- Last modified
- 2026-06-25T16:58:29.000Z
Compatibility and lineage
Reported languages: en, zh, de, ko
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.