AI · Video
Auto Caption Generator
Transcribes speech with OpenAI Whisper and adds accurate, timed captions to videos automatically using FFmpeg.
Overview
The Auto Caption Generator automates subtitles for videos. It pulls the audio track out of a video, transcribes it with OpenAI’s Whisper speech-to-text model, and turns the transcript into synchronised captions.
It makes video content more accessible and searchable without manual typing, and works with many video formats thanks to FFmpeg.
Key features
01Speech-to-textOpenAI Whisper converts spoken dialogue into accurate text.
02Synced captionsTranscripts are timed and formatted as subtitles.
03Video processingFFmpeg extracts audio and handles format conversion.
04Easy setupChocolatey automates installing the tools on Windows.
How it works
- Load a video and extract its audio with FFmpeg.
- Transcribe the audio with the Whisper model.
- Format the text into timed caption segments.
- Render the captions onto the video.
More screenshots
Contact
Let’s build something great together
Have a project, a role or just an idea? Send a message and I’ll get back to you soon.
Send a message
Your message comes straight to my inbox. I usually reply within a day or two.