Quickstart

Create your first Velo video in minutes — upload a recording or PDF and let the AI handle pacing, audio, and narration.

Velo transforms raw screen recordings and documents into polished video messages by automatically managing pacing, audio quality, and narration. This guide covers the initial steps to generate your first project using the upload workflow.

Select a Project Type

When starting a new project, you can choose from three distinct methods to provide content: Capture screen records your screen directly using the Velo extension; Upload a recording or PDF imports existing MP4, MOV, or PDF files; and Paste a link generates a video from a web URL (currently in beta).

The Velo dashboard offers multiple starting points for video generation.

Upload Content and Choose a Voice

After choosing to upload a recording, select the desired file from your local storage. Once the upload is confirmed, select a narration style. You can use your own cloned voices or choose from a list of Public Voices categorized by tone - Drew (casual, curious, and fun), Viraj (energetic and confident), Hope (professional and clear), or Monika (deep and natural).

Select a voice profile to handle the automated narration of your video.

Process and Refine Your Video

After confirming your voice selection, the system begins generating the “first look.” During this phase, the platform automatically separates and polishes the audio, transcribes speech to text, and applies smart zooms while matching the new audio to the video frames.

Velo provides real-time status updates as it processes the video and audio.

Once the video is generated, you can preview the results in the right-hand panel. Use the Quick actions menu to Disable Zooms, Add Music, Add Logo, or Rewrite script if further adjustments are needed. When ready for distribution, select “Get a sharable link” to copy the project URL.

Review the final output and use quick actions for last-minute refinements.

The completed Velo is a professional, narrated video message with consistent pacing and polished audio, ready for your audience.