Text-to-Speech
Transformers
Safetensors
higgs_multimodal_qwen3
text-generation
speech-generation
voice-agent
expressive-speech
controllable-tts
multilingual-tts
Instructions to use bosonai/higgs-tts-3-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bosonai/higgs-tts-3-4b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="bosonai/higgs-tts-3-4b")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("bosonai/higgs-tts-3-4b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
参考音频问题
#22 opened 15 days ago
by
evan-cheng
MLX/Mac Limited Usage
1
#21 opened 15 days ago
by
nhe-ai
Control tags (<|emotion:...|>, <|style:...|>, <|prosody:...|>) shift the speaker's timbre — happens both with and without voice cloning
#20 opened 19 days ago
by
Ankerf
Glitches and Silence
8
#18 opened 29 days ago
by
NezzConstantine
Cross-linguistic Voice Clone Stability
4
#17 opened about 1 month ago
by
sailorjs0804
Higgs Audio Studio — portable 1-click local build (Windows, + Linux/macOS via Pinokio)
🔥 5
1
#15 opened about 1 month ago
by
nerualdreming
How to use Control Tokens?
1
#13 opened about 1 month ago
by
Syams
Control Tokens not works
1
#11 opened about 1 month ago
by
Syams
Does Higgs Audio v3 only work on Linux?
1
#10 opened about 1 month ago
by
Syams
Tupt sound at regular intervals of time
3
#8 opened about 1 month ago
by
Venom2212
Doesnt work on Windows
3
#7 opened about 1 month ago
by
PierrunoYT
Run Higgs without SGlang
10
#6 opened about 2 months ago
by
Syams
Finetune guide
#5 opened about 2 months ago
by
rastegar
ComfyUI Ready 🎉
🚀🔥 5
1
#4 opened about 2 months ago
by
drbaph
VRAM use
9
#3 opened about 2 months ago
by
JacobR22
How to handle mixed Mandarin and Cantonese text when the model does not support per‑word language selection?
2
#2 opened about 2 months ago
by
sgxtj