pnkvalavala/digitaltwin

Using a single image and just 10 seconds of sample audio, our project enables you to create a video where it appears as if you're speaking the desired text.

33
/ 100
Emerging

This project helps you create videos where it looks like a person is speaking your desired text, using just a single image and a 10-second audio sample of their voice. It takes an image of someone and a short audio clip of their voice, then generates a video with accurate lip-sync for any text you provide. This is ideal for content creators, marketers, or educators who need to quickly produce personalized or narrated videos.

No commits in the last 6 months.

Use this if you need to generate a realistic video of someone speaking a specific script, based only on their image and a short voice sample.

Not ideal if you require very long, complex videos with multiple speakers or intricate visual effects, as its primary focus is on generating speech and lip-sync from a static image.

content-creation video-production marketing e-learning digital-communication
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

40

Forks

12

Language

Jupyter Notebook

License

Last pushed

Sep 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/pnkvalavala/digitaltwin"

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