AI Captions

Overview

QuickSnip offers two types of AI-powered captions:

• Studio captions — Generated locally on your machine using Whisper AI models. Available in the studio editor after recording in Studio mode. This article covers studio captions.
• Instant captions — Generated automatically in the cloud after uploading a recording in Instant mode. These use DeepGram for fast cloud-based transcription.

Generate Captions

Captions are available in Studio mode. After recording:

1. Open the studio editor
2. Navigate to the Captions tab
3. Select your preferred transcription model
4. If this is your first time, click Download to download the model (one-time step)
5. Choose the language (defaults to Auto Detect)
6. Click Generate Captions

Generation typically takes 10–30 seconds depending on the length of your recording. If you've already generated captions, the button changes to Regenerate Captions.

Choose a Model

QuickSnip offers two local Whisper models with different speed and accuracy trade-offs:

Model	Size	Speed	Accuracy	Best For
Small	466 MB	Faster	Good	Quick recordings, clear audio
Medium	1.5 GB	Moderate	Better	Technical terms, accented speech

Models are downloaded once and stored locally. You can use them offline after the initial download.

Preview Captions

After generation, captions appear overlaid on your video preview in real time. Play through your recording to verify accuracy.

Edit Captions

If the AI gets a word wrong, you can manually edit captions in the Caption Segments list below the video preview:

1. Find the segment you want to edit in the list
2. Edit the caption text in the text field
3. Adjust the start and end times if needed
4. Click Add at Current Time to insert a new caption segment at the current playback position
5. Delete any unwanted segments with the delete button

This is especially useful for product names, brand terms, or technical jargon that the AI might not recognize.

Caption Styling

Customize how captions appear on your video:

• Position — 6 placement options: top-left, top-center, top-right, bottom-left, bottom-center, bottom-right
• Font size — Slider from 12px to 100px
• Font family — Sans-serif, serif, or monospace
• Font weight — Normal, medium, or bold
• Font color — Full color picker with hex input
• Background color — Color picker for the caption background
• Background opacity — Slider from 0–100%
• Active word highlight — Toggle to highlight the currently spoken word
• Highlight color — Color picker for the active word highlight

Language Support

QuickSnip supports transcription in the following languages. Select your language from the dropdown before generating captions — the default is Auto Detect.

• Auto Detect
• English
• Spanish
• French
• German
• Italian
• Portuguese
• Dutch
• Polish
• Russian
• Turkish
• Japanese
• Korean
• Chinese

What's Next

• Audio Settings — Make sure your audio is set up correctly
• Recording Modes — Use Studio mode for caption support
• Sharing Basics — Share your captioned recording