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", dtype="auto") - Notebooks
- Google Colab
- Kaggle
ke/add_agentsmd
#9
by bytebecky - opened
No description provided.
- AGENTS.md — a self-contained operational guide for AI coding agents. Given a proper GPU, an agent can follow it end-to-end to stand up a local service (it also covers the hosted API and inline control-tag rules), without needing the repo cloned first.
- PROMPTING.md — a guide for writing the target text: how to add emotion / prosody / style / sound-effect control via inline tags (full 43-tag catalog with placement rules and examples).
- README.md — added a reference to PROMPTING.md from the Control Tokens section. Did not add a back-reference to AGENTS.md, since AGENTS.md is meant to stand alone for agents rather than be part of the human-facing README flow.
bytebecky changed pull request status to open
LGTM!
SilinMeng0510 changed pull request status to merged