DragonLiu1995/video-to-audio-through-text

[NeurIPS 2024] Code, Dataset, Samples for the VATT paper “ Tell What You Hear From What You See - Video to Audio Generation Through Text”

31
/ 100
Emerging

This project helps video creators, educators, and content strategists automatically add realistic audio to silent videos or generate audio descriptions. It takes a video and an optional text prompt, then produces relevant audio and, if desired, a text description of that audio. This is perfect for anyone needing to enhance video content with rich, context-aware sound without manual sound design.

No commits in the last 6 months.

Use this if you need to generate high-quality, context-relevant audio or audio descriptions for videos, especially when you want to guide the audio generation with specific text prompts.

Not ideal if you're looking for a simple drag-and-drop tool for quick, casual video edits, as it requires some technical setup and a GPU.

video-editing content-creation media-production digital-storytelling accessibility
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

36

Forks

2

Language

Python

License

Last pushed

Jul 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/DragonLiu1995/video-to-audio-through-text"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.