Skip to main content
AI Transcribe works specifically for generating caption tracks from video audio. It converts spoken content into structured subtitle files that can be directly used inside the player.

​
How It Works

  1. User clicks Transcribe on a video.
  2. A modal opens with language selection.
  3. User selects one or multiple target languages.
  4. Pricing is calculated based on duration × selected languages.
  5. User confirms transcription.
  6. The system generates caption files.
  7. Generated captions are attached to the video automatically.

​
Caption Features

  • Generates subtitle-ready caption files
  • Outputs in WebVTT (.vtt) format
  • Time-synced captions with accurate timestamps
  • Separate caption track for each selected language
  • Automatically linked to the video player
  • Supports multiple language captions per video
  • Default caption selection support
  • Can be turned On / Off inside the player
  • Re-generate captions for additional languages
  • Secure caption storage per video

​
Integration with Player

  • Captions appear in the Subtitle / CC menu
  • Users can switch between available languages
  • Works seamlessly with HLS playback
  • No manual upload required after transcription
  • Dynamically loads caption tracks per video

​
Pricing

  • Cost: $0.5 per minute for each selected language
  • Total cost = Video duration × Number of selected languages
Example:
  • 10-minute video
  • 2 selected languages
    → Total cost: $10