Text-to-Speech
Transformers
Safetensors
English
higgs_multimodal_qwen3
feature-extraction
tts
voice-cloning
higgs-audio
qwen3
custom_code
Instructions to use multimodalart/higgs-audio-v3-tts-4b-transformers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use multimodalart/higgs-audio-v3-tts-4b-transformers with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="multimodalart/higgs-audio-v3-tts-4b-transformers", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("multimodalart/higgs-audio-v3-tts-4b-transformers", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
multimodalart HF Staff
Server-side copy weights + tokenizer.json from bosonai/higgs-audio-v3-tts-4b
6e048c7 verified - Xet hash:
- 8dc3b49164a491e0e02dee30ea3f89ecba7cf4389b6bfc71216e60337af5d2a3
- Size of remote file:
- 9.31 GB
- SHA256:
- 2f7965264c360b38180885006944aa16bd1de20f4e6cff79f6473bfcf8ae3d5a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.