Zum Inhalt springen

ModelAufgelistetExtern

Higgs Audio v3 Tts 4b

boson-higgs-audio-v3-research-and-non-commercial-license

Quellehuggingface.co/onnx-community/higgs-audio-v3-tts-4b/tree/ecc25d6cc6e48909401bfa7ce5ac95e84f41f331

ArtOtherVersionRevision ecc25d6CBewertung

Modellquelle

Art: Other
Dateigröße: 296 KB–1,45 GB
Version: vRevision ecc25d6
Aktualisiert: 25. Sept. 2026
Downloads: 0
Quelle: Hugging Face

Quellenauszug

boson-higgs-audio-v3-research-and-non-commercial-license

Quellen

1 Quelle

Hugging FacePrimärVersion ecc25d6cc6e48909401bfa7ce5ac95e84f41f331

huggingface.co/onnx-community/higgs-audio-v3-tts-4b/tree/ecc25d6cc6e48909401bfa7ce5ac95e84f41f331

Verifiziert 6. Sept.

Download files

Modellartefakte

40 Artefakte

cpu_fp16/audio_embed.onnx

onnx · 40,1 MB · SHA-256 ce1354ec3a9b…e221 · Hugging Face

cpu_fp16/audio_encoder.onnx

onnx · 624 MB · SHA-256 14a57dab2eaa…2050 · Hugging Face

cpu_fp16/audio_heads.onnx

onnx · 40,1 MB · SHA-256 93c6fd20d939…af02 · Hugging Face

cpu_fp16/audio_tokenizer.onnx

onnx · 82,5 MB · SHA-256 ac0f0711a6c2…2762 · Hugging Face

cpu_fp16/llm_decoder.onnx

onnx · 909 KB · SHA-256 467c3c6d9ac9…626e · Hugging Face

cpu_fp16/text_embed.onnx

onnx · 742 MB · SHA-256 1c4834443896…8255 · Hugging Face

cpu_fp32/audio_embed.onnx

onnx · 80,2 MB · SHA-256 a8a71a059cbd…e8ec · Hugging Face

cpu_fp32/audio_encoder.onnx

onnx · 624 MB · SHA-256 14a57dab2eaa…2050 · Hugging Face

cpu_fp32/audio_heads.onnx

onnx · 80,2 MB · SHA-256 5daffe6cae0b…d190 · Hugging Face

cpu_fp32/audio_tokenizer.onnx

onnx · 82,5 MB · SHA-256 ac0f0711a6c2…2762 · Hugging Face

cpu_fp32/llm_decoder.onnx

onnx · 310 KB · SHA-256 8be491865dd6…c999 · Hugging Face

cpu_fp32/text_embed.onnx

onnx · 1,45 GB · SHA-256 bea40511babe…3b77 · Hugging Face

cpu_int4/audio_embed.onnx

onnx · 12,8 MB · SHA-256 521bfbafc0c7…c71b · Hugging Face

cpu_int4/audio_encoder.onnx

onnx · 624 MB · SHA-256 14a57dab2eaa…2050 · Hugging Face

cpu_int4/audio_heads.onnx

onnx · 12,8 MB · SHA-256 e29357306223…e3a0 · Hugging Face

cpu_int4/audio_tokenizer.onnx

onnx · 82,5 MB · SHA-256 ac0f0711a6c2…2762 · Hugging Face

cpu_int4/llm_decoder.onnx

onnx · 375 KB · SHA-256 b96d86f69d6b…9285 · Hugging Face

cpu_int4/text_embed.onnx

onnx · 742 MB · SHA-256 1c4834443896…8255 · Hugging Face

cuda_fp16/audio_embed.onnx

onnx · 40,1 MB · SHA-256 ce1354ec3a9b…e221 · Hugging Face

cuda_fp16/audio_encoder.onnx

onnx · 624 MB · SHA-256 14a57dab2eaa…2050 · Hugging Face

cuda_fp16/audio_heads.onnx

onnx · 40,1 MB · SHA-256 93c6fd20d939…af02 · Hugging Face

cuda_fp16/audio_tokenizer.onnx

onnx · 82,5 MB · SHA-256 ac0f0711a6c2…2762 · Hugging Face

cuda_fp16/llm_decoder.onnx

onnx · 310 KB · SHA-256 62d355ee7694…8009 · Hugging Face

cuda_fp16/text_embed.onnx

onnx · 742 MB · SHA-256 1c4834443896…8255 · Hugging Face

cuda_fp32/audio_embed.onnx

onnx · 80,2 MB · SHA-256 a8a71a059cbd…e8ec · Hugging Face

cuda_fp32/audio_encoder.onnx

onnx · 624 MB · SHA-256 14a57dab2eaa…2050 · Hugging Face

cuda_fp32/audio_heads.onnx

onnx · 80,2 MB · SHA-256 5daffe6cae0b…d190 · Hugging Face

cuda_fp32/audio_tokenizer.onnx

onnx · 82,5 MB · SHA-256 ac0f0711a6c2…2762 · Hugging Face

cuda_fp32/llm_decoder.onnx

onnx · 296 KB · SHA-256 00fe82f76179…04ba · Hugging Face

cuda_fp32/text_embed.onnx

onnx · 1,45 GB · SHA-256 bea40511babe…3b77 · Hugging Face

cuda_int4/audio_embed.onnx

onnx · 12,8 MB · SHA-256 521bfbafc0c7…c71b · Hugging Face

cuda_int4/audio_encoder.onnx

onnx · 624 MB · SHA-256 14a57dab2eaa…2050 · Hugging Face

cuda_int4/audio_heads.onnx

onnx · 12,8 MB · SHA-256 e29357306223…e3a0 · Hugging Face

cuda_int4/audio_tokenizer.onnx

onnx · 82,5 MB · SHA-256 ac0f0711a6c2…2762 · Hugging Face

cuda_int4/llm_decoder.onnx

onnx · 371 KB · SHA-256 7bcedb613c4b…5d09 · Hugging Face

cuda_int4/text_embed.onnx

onnx · 742 MB · SHA-256 1c4834443896…8255 · Hugging Face

openvino_int4/audio_embed.onnx

onnx · 12,8 MB · SHA-256 521bfbafc0c7…c71b · Hugging Face

openvino_int4/audio_heads.onnx

onnx · 12,8 MB · SHA-256 e29357306223…e3a0 · Hugging Face

openvino_int4/audio_tokenizer.onnx

onnx · 82,5 MB · SHA-256 ac0f0711a6c2…2762 · Hugging Face

openvino_int4/llm_decoder.onnx

onnx · 375 KB · SHA-256 b96d86f69d6b…9285 · Hugging Face

Quellenauszüge

2 Auszüge

Readme6. Sept.huggingface.co/onnx-community/higgs-audio-v3-tts-4b

--- license: other license_name: boson-higgs-audio-v3-research-and-non-commercial-license license_link: LICENSE language: - 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 - ka - kab - kam - kea - kk - kn - ko - ky - la - lb - lg - ln - lt - luo - lv - mhr - mi - mk - ml - mn - mr - ms - mt - ne - nl - no - nso - ny - oc - om - pa - pl - ps - pt - ro - ru - rw - sd - sk - sl - sn - so - sq - sr - sv - sw - ta - te - tg - tl - tr - ug - uk - umb - ur - uz - vi - xh - zh - zu tags: - text-to-speech - speech-generation - voice-agent - expressive-speech - controllable-tts - multilingual-tts - onnx - onnxruntime pipeline_tag: text-to-speech library_name: onnxruntime base_model: - bosonai/higgs-audio-v3-tts-4b --- # Higgs Audio v3 TTS <div align="left" style="display: flex; justify-content: flex-start; margin-top: 10px;"> <a href="https://www.boson.ai/blog/higgs-audio-v3-tts"> <img src="https://img.shields.io/badge/💚-Boson%20Blog-228B22" style="margin-right: 5px;"> </a> </div> Higgs Audio v3 TTS 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. > [!TIP] > Released for research and non-commercial use under the **Boson Higgs Audio v3 Research and Non-Commercial License**. Production, hosted APIs, or revenue-generating use requires a separate commercial license. Prohibited: voice cloning without consent, impersonation, fraud, election deception, biometric surveillance, or any unlawful use. ![Higgs Audio v3 TTS Architecture](./assets/model_architecture.png) 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. | Component | Spec | |---|---| | Backbone | ~4B autoregressive decoder (36 L,...

Note6. Sept.huggingface.co/onnx-community/higgs-audio-v3-tts-4b

Source context: 0 downloads · 14 likes · Pipeline text-to-speech · Library onnxruntime · Repo onnx-community/higgs-audio-v3-tts-4b