
uhhlt/story-emb
Updated
β’
15
β’
1
a tiny vision language model
Generates a sound effect that matches video shot
Real-time object detection w/ π€ Transformers.js
Edit audios with text prompts
Generate music from text prompts πΆ
Get Music from Generated Spectrogram with Diffusion
Generate audio and waveform video from text
Generate music from text and melody descriptions