AI Captions

Zidi automatically generates accurate captions for your videos using AI-powered speech recognition. Captions improve accessibility, engagement, and SEO.

How It Works

1. Open any video in your workspace.
2. Click Generate Captions in the AI Tools panel.
3. The AI transcribes your video audio with word-level timestamps.
4. Captions appear as an overlay on your video player.

Supported Languages

Zidi uses AssemblyAI with automatic language detection. It supports 20+ languages including:

• English, Spanish, French, German, Italian, Portuguese
• Chinese, Japanese, Korean
• Arabic, Hindi, Turkish, Russian
• Dutch, Polish, Swedish, and more

Caption Styling

Customize how captions appear in the video editor:

• Font size — Small, medium, large.
• Position — Top, center, or bottom of the video.
• Background — Solid, semi-transparent, or none.
• Colors — Text and background colors.

Editing Captions

After generation, you can edit any caption text directly. The transcript panel shows all captions with timestamps — click any segment to edit.

Translation

Translate your captions into other languages directly from the transcript panel. Click Translate and select the target language.

Credits

Each caption generation uses 1 credit regardless of video length.