CaptionG — Audio & Video Captioning
Desktop App

CaptionG — Audio & Video Captioning

← Back to projects

Overview

CaptionG turns audio or video into text and subtitles with a fast desktop workflow. Users can edit timings and captions before exporting clean SRT, VTT, or TXT files.

How it works

  • 1.Users drop an audio or video file into the desktop app.
  • 2.Video files are converted to clean audio before transcription begins.
  • 3.Whisper transcribes the content and builds timed caption segments.
  • 4.An editor lets users adjust timings, wording, and line breaks.
  • 5.Exports are generated in SRT, VTT, or TXT formats.

Key features

  • Three workflows for audio and video transcription
  • Built-in caption editor with timeline controls
  • Smart caption formatting and cleanup rules
  • Exports to SRT, VTT, and TXT
  • Drag-and-drop upload with format validation

Tech Stack

PythonPySide6WhisperFFmpegSciPy

Want something built like this?

Get in Touch