TencentARC/AudioStory

AudioStory: Generating Long-Form Narrative Audio with Large Language Models

32
/ 100
Emerging

AudioStory helps content creators, animators, and video editors generate long, coherent soundscapes and narratives for their projects. You provide text descriptions or existing video captions, and it produces high-quality, continuous audio, complete with sound effects, music, and spoken elements. It's ideal for anyone needing to create immersive sound without extensive audio production skills.

299 stars. No commits in the last 6 months.

Use this if you need to generate detailed, lengthy audio tracks, such as background sounds for animations, dubbing for videos, or natural sound narratives from text descriptions.

Not ideal if you primarily need to generate short, isolated sound effects or individual voice clips without a complex, evolving narrative.

animation video-editing content-creation audio-storytelling sound-design
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 7 / 25
Community 13 / 25

How are scores calculated?

Stars

299

Forks

22

Language

Jupyter Notebook

License

Last pushed

Sep 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/TencentARC/AudioStory"

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