Running on Zero Featured 1.75k Dia 1.6B ๐ฏ 1.75k Generate realistic dialogue from a script, using Dia!
HuggingFaceTB/SmolVLM2-500M-Video-Instruct Image-Text-to-Text โข Updated Apr 8, 2025 โข 208k โข 120
microsoft/Phi-4-multimodal-instruct Automatic Speech Recognition โข Updated Dec 10, 2025 โข 334k โข 1.58k
Running Featured 353 Kokoro Text-to-Speech (WebGPU) ๐ฃ 353 High-quality speech synthesis powered by Kokoro TTS
mlx-community/SmolVLM2-500M-Video-Instruct-mlx Video-Text-to-Text โข Updated Feb 20, 2025 โข 1.91k โข 18
Runtime error Featured 33 CLIPnCROP ๐ 33 Extract and crop image sections based on text description