The AI agent analyses your uploaded file, extracting screen activity, narration audio, or document content and uses it to build a fresh, clean video. It applies optimised pacing, smart zooms, and AI narration to the output automatically.
Supported formats: MP4, MOV, and PDF.
Step 1: Upload your file
From the dashboard, click Upload a recording or PDF. Select your file from your computer. Once uploaded, the AI agent begins analysing the content.
Step 2: Wait for analysis
Choose a file from your browser. Once the file is opened, it is added to the platform for analysis.
Choose the upload option to start a new project from an existing file.
Step 3: Select your voice
Once analysis is complete, choose the voice that will narrate your video.
- My Voices - uses your personal VeloTwin voice clone
- Public Voices - uses a standard AI narrator from Velo’s voice library
If you haven’t set up a Voice Clone yet, select a Public Voice to continue. You can set up your VeloTwin later and rebuild the video with your own voice.
Step 4: Confirm and generate
Confirm your selection to begin video generation. The agent will prompt you to proceed - click “Yes, make my Velo” to start.
A progress bar shows the status as the agent builds the final video. You can safely navigate away from the page - Velo will send you an email notification when your video is ready.
Track the status of your video as the AI agent applies final edits.
The finished video features your uploaded content with cleaned-up pacing, synchronised AI narration, and automatic zoom events applied to key interactions. 
