CaptainYi
← Back to Tools

Vid2Text Pro

Live

Downloads YouTube audio via yt-dlp, splits into 10-minute chunks, transcribes with OpenAI Whisper, and outputs txt / srt / vtt / json.

This page shows simulated demo data for illustration purposes only.

24

Videos Processed

94.9%

Avg Accuracy

18h 30m

Total Duration

24

Docs Generated

Video TitleDurationAccuracyFormatStatus
Food Safety Induction Training – Module 11h 14m96.2%.srtCompleted
Monthly Operations Review – March 202658m94.8%.txtCompleted
HACCP Awareness Session for New Staff2h 02m95.5%.jsonCompleted
Supplier Onboarding Presentation – Q145m93.1%.vttCompleted
Kitchen SOPs Walkthrough – Prep Area B32m.srtProcessing
Annual Food Safety Audit Recording1h 38m.jsonQueued

Sample Output

.srt
1
00:00:00,000 --> 00:00:05,420
Welcome to today's food safety induction training.

2
00:00:05,420 --> 00:00:10,840
We will cover HACCP principles, temperature control,
and critical control points.

3
00:00:10,840 --> 00:00:16,310
All employees are required to complete this module
before working in food preparation areas.

Source Repository

ian60012/Vid2Text-Pro

High-precision YouTube video-to-text transcription powered by OpenAI Whisper and yt-dlp. Splits audio into 10-min chunks, merges with correct timestamps, outputs txt / srt / vtt / json.

Tech Stack

PythonOpenAI Whisperyt-dlppydubDocker
View on GitHub →