Turning videos into process documentation has never been easier. With Whale’s Video-to-Guide feature, you can upload any instructional video — whether it’s a screen recording, equipment demo, or training walkthrough — and our AI automatically transforms it into an editable step-by-step guide.
Whale doesn’t just transcribe the audio — it analyzes the visuals too. Every movement, click, and action is detected to build accurate, clickable instructions that link directly to specific timestamps in the video. This is perfect for onboarding, SOP creation, or documenting complex workflows.
How to Create a Step-by-Step Guide from a Video
Option 1: From the Main “+” Button
Step 1: Click the ➕ icon at the top-right corner of your Whale screen
Step 2: Select “Import Video”
Step 3: Upload your video and click Next
Step 4: Give your new card a title and choose a location in your workspace
Step 5: Click Next to let Whale process your video
Whale will automatically analyze the video and generate a new card containing the step-by-step breakdown — each step linked to the moment it happens in the video.
Option 2: From Within a Playbook
You can also start directly from a playbook (Grid or List View):
Click Create New Card
Choose Import Video
Follow the same steps above to upload and generate the guide
Example
You’ve recorded a 2-minute video walking through a new software feature. Once uploaded, Whale turns that into a guide with steps like:
“Click the ‘Settings’ icon”
“Navigate to ‘Preferences’”
“Enable the integration toggle”
Each step includes a clickable link that jumps to the exact moment in the video.
💡 Bonus: Use a Native Whale Screen Recording
If you used Whale’s built-in screen recorder, the video will automatically appear in your card. To generate steps:
Click on the video from the card editor
Choose Generate Steps
Whale will create a new card with the extracted guide
⚠️ This process doesn’t overwrite the original card — it creates a new one in the same playbook.
With Whale, your training content becomes instantly reusable, searchable, and actionable — no more manual breakdowns or hours spent transcribing videos.