videocaptiontool / README.md
hellorahulk's picture
Add video caption app with Whisper auto-captioning and styling options
2302206

A newer version of the Gradio SDK is available: 5.29.0

Upgrade
metadata
title: Videocaptiontool
emoji: πŸ‘
colorFrom: gray
colorTo: pink
sdk: gradio
sdk_version: 5.24.0
app_file: app.py
pinned: false

Video Caption Generator

This tool allows you to add captions to your videos with precise control over styling and positioning. You can either auto-generate captions using Whisper AI speech recognition or provide your own captions in SRT, ASS, or VTT format.

Features

  • Auto Caption Generation: Extract and transcribe audio from your video using OpenAI's Whisper model
  • Manual Caption Support: Input your own captions in popular formats (SRT, ASS, VTT)
  • Customizable Styling: Control font, size, color, and positioning of captions
  • High-Quality Output: Burn captions directly into your video with FFmpeg

How to Use

  1. Upload your video file
  2. Choose whether to auto-generate captions or provide your own
  3. Customize font, size, color, and alignment
  4. Click "Generate Captioned Video" and wait for processing
  5. Download the resulting video with embedded captions

Perfect for creating accessible content, adding subtitles to multilingual videos, or emphasizing important information in educational content.

Note

Processing time depends on video length and complexity. Auto-caption generation utilizes Whisper and may take longer for larger files.

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference