bosonai/higgs-audio-v2-generation-3B-base
Text-to-Speech
•
6B
•
Updated
•
314k
•
637
ASR demo using onnx-asr
Canary 1B Flash demo
Interactive Portrait Animation and Editing
Swap faces in images and enhance them if desired
Free Text-To-Speech generator with Emotion control (OpenAI)
Lightweight vision for efficient deployment
Convert images to structured documents and answer questions
Chat with Xiaomi MiMo-Audio using voice
Generate expressive speech from text with emotion control
Generate images from text prompts
DeepResearch with the fathom search and synthesizer models
Generate Hollywood Style Actors on your Local Machine
Qwen3-VL / Qwen2.5-VL