equilicore/see-and-tell
See and Tell | Assistant to Experience Video Content With Ears
This tool helps people with visual impairments enjoy videos and other visual content by generating detailed audio descriptions. You provide a video file, and it outputs a new version of the video where a clear voice narrates what's happening on screen, without interrupting dialogue. This is for individuals who are blind or have low vision, or anyone who wants to experience visual content primarily through sound.
No commits in the last 6 months.
Use this if you or someone you know struggles to enjoy visual content like movies or TV shows due to visual impairment, or if you want to listen to a video's visual details when you can't actively watch it.
Not ideal if you need perfectly precise, real-time descriptions for highly dynamic or complex scenes with many characters, as it might occasionally misidentify a character or describe a slightly different frame.
Stars
21
Forks
1
Language
Python
License
—
Category
Last pushed
Oct 03, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/equilicore/see-and-tell"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BishopFox/eyeballer
Convolutional neural network for analyzing pentest screenshots
aws-samples/amazon-rekognition-custom-labels-demo
A demo to test Custom Labels with models trained by Amazon Rekognition
EddyVerbruggen/nativescript-plugin-firebase
:fire: NativeScript plugin for Firebase
ZeroBone/OfficialEye
An advanced AI-powered generic document-analysis tool
GuiltyNeuron/SmartGlasses
Smart wearable device project