Voiceover to video
Build a complete video around finished narration
Upload the approved voiceover. VideoGen transcribes it, creates matching visuals, adds captions, and returns an editable project.
Voice-led videos made with VideoGen
Examples of narration driving visual timing, captions, and scene selection across different formats.
Lesson built around an uploaded voiceover
The original narration sets the timing while VideoGen adds matching visuals and captions.
Narrated training walkthrough
Clear spoken instruction paired with supporting visuals for an internal how-to video.
Narrated proposal walkthrough
A business presentation paced around narration with captions and visual continuity.
Keep the approved audio at the center
Use the original recording as the source of truth while VideoGen builds the visual production around it.
Automatic transcription
Use the uploaded narration to determine timing, captions, and visual pacing.
Matching visuals
Generate or select b-roll that follows the meaning and timing of the voiceover.
Captions and branding
Set caption styling and a logo in the workflow request, then refine the editable project before export.
How voiceover to video works
Upload the narration
Upload the approved audio, optionally attaching a transcript before starting the workflow.
Choose the visual direction
Select stock footage or describe an AI visual style, pacing, and output format.
Generate and review
VideoGen builds the timed scenes, captions, and edits around the original audio.
Generate a video from an uploaded voiceover
Upload the audio first, then pass its file id to the workflow.
View complete API documentationcurl -X POST https://api.videogen.io/v1/workflows/voiceover-to-video \
-H "Authorization: Bearer sk_videogen_live_..." \
-H "Content-Type: application/json" \
-d '{
"fileId": "vg_file_...",
"visualStyle": {
"type": "AI_IMAGE",
"aiStyle": "clean editorial illustrations with subtle depth"
},
"visualPacing": "MEDIUM",
"quality": "HIGH",
"remixActions": [
{
"type": "CONVERT_IMAGES_TO_VIDEOS",
"motionPrompt": "slow cinematic push-in",
"muteOutputVideos": true,
"quality": "HIGH"
},
{
"type": "ADD_TRANSITIONS",
"sectionTransition": "DYNAMIC",
"assetTransition": "FADE"
}
]
}'Voiceover to video use cases
Podcasts and interviews
Turn selected audio segments into visual social and educational content.
Executive communications
Add visuals and captions to approved leadership narration.
Training and education
Build structured lessons around expert-recorded audio.
Frequently asked questions
- Does VideoGen change the uploaded voiceover?
- No. The uploaded audio remains the narration source while VideoGen builds visuals and edits around it.
- Can I provide my own transcript?
- Yes. Attach a transcript when uploading the file to skip automatic transcription.
- Can I direct what appears during specific moments?
- Yes. Provide timed scene descriptions or production notes to guide the visuals.