Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

bosonai
/
higgs-audio-v3-tts-4b

Text-to-Speech
Transformers
Safetensors
higgs_multimodal_qwen3
text-generation
speech-generation
voice-agent
expressive-speech
controllable-tts
multilingual-tts
Model card Files Files and versions
xet
Community
12

Instructions to use bosonai/higgs-audio-v3-tts-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use bosonai/higgs-audio-v3-tts-4b with Transformers:

    # Use a pipeline as a high-level helper
    from transformers import pipeline
    
    pipe = pipeline("text-to-speech", model="bosonai/higgs-audio-v3-tts-4b")
    # Load model directly
    from transformers import AutoModelForSeq2SeqLM
    model = AutoModelForSeq2SeqLM.from_pretrained("bosonai/higgs-audio-v3-tts-4b", dtype="auto")
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

ke/add_mac_cfui_deployment

#12 opened about 20 hours ago by
bytebecky

Control Tokens not works

1
#11 opened about 22 hours ago by
Syams

Does Higgs Audio v3 only work on Linux?

1
#10 opened 1 day ago by
Syams

Tupt sound at regular intervals of time

3
#8 opened 2 days ago by
Venom2212

Doesnt work on Windows

3
#7 opened 3 days ago by
PierrunoYT

Run Higgs without SGlang

7
#6 opened 4 days ago by
Syams

Finetune guide

#5 opened 4 days ago by
rastegar

ComfyUI Ready 🎉

❤️🔥 5
1
#4 opened 6 days ago by
drbaph

VRAM use

8
#3 opened 6 days ago by
JacobR22

How to handle mixed Mandarin and Cantonese text when the model does not support per‑word language selection?

2
#2 opened 6 days ago by
sgxtj
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs