Skip to main content

​
Supported inputs and limits

  • File content: Must be voiceover.
  • File type: MP3, M4A, WAV, AAC, OGG, Opus, FLAC, MP4, MOV, M4V, and WebM.
  • File size: up to 50 MB.
  • Voiceover length: up to 5 minutes.
  • Picture styles: 25 visual styles to choose from.
  • Aspect ratios: 16:9 landscape, 9:16 portrait, or 1:1 square.
  • Visual pacing: Calm uses longer shots, Balanced uses a natural mix, and Dynamic changes visuals more frequently.
  • Limits: up to 200 scenes and up to 8 recurring visual references.

​
How to use Audio to Image Video

The Audio to Image Video creation screen with Add speech, picture style, aspect ratio, and visual pacing controls. Add speech, choose a picture style, aspect ratio, and visual pacing, then create a story plan.
  1. Open Audio to Image Video. You can also go to Opus Labs, find Audio to Image Video, and select Try it now.
  2. In Add speech, upload or record an audio or video file. If you upload a video, only its audio is used.
  3. Choose a picture style, aspect ratio, and visual pacing.
  4. Select Create story plan.
  5. Review the plan. For each scene, edit the visual description or select Regenerate description.
A scene in the story plan with options to edit the visual description or regenerate it. Open a scene to edit what it should show or regenerate its description.
  1. To change a visual reference, select Edit references, edit its description, and select Redraw.
The Edit references panel for updating how a recurring person, place, or object should look. Edit how a recurring person, place, or object should look, then select Redraw.
  1. Review the displayed credit price, then select Generate video to confirm the plan and start generation.
  2. When the video is ready, preview it and select Download MP4.
The finished story preview with scene thumbnails and a Download MP4 button. Preview the finished story, choose a scene, or select Download MP4.

​
Find your projects

Select Projects in Audio to Image Video. You will see all your past projects here. The Projects list in Audio to Image Video showing past story projects and their status.

​
Credits

Audio to Image Video and OpusClip use the same credit balance. The Generate video button shows the current price for the reviewed story before you spend credits. The displayed amount is reserved when generation starts. Credits are charged only when the video finishes generating. If generation cannot finish and the reservation is released, no credits are charged.

​
Troubleshooting

​
The upload is rejected

Confirm that the file contains playable audio, is no larger than 50 MB, and is no longer than 5 minutes. Try one of the supported audio or video formats listed above.

​
Recording does not start

Allow microphone access when your browser asks. If access was previously blocked, open the site permissions for labs.opus.pro, enable the microphone, and try Record again.

​
Frequently asked questions

​
Can I close the page while Audio to Image Video is working?

Yes, after the initial upload finishes and the saved project opens. Planning, visual generation, and MP4 rendering continue in the background. Return from Projects. Keep the page open during the initial upload.

​
What happens when I upload a video?

Audio to Image Video uses the audio track as the voiceover. It does not reuse the source video’s pictures; it creates new illustrated scenes.

​
Does correcting the transcript change my voiceover?

No. Transcript corrections help the scene plan and narration text, but the exported video continues to use the original audio.

​
Why does my story have no visual references?

Some stories do not repeat a person, place, or object often enough to need a reusable reference. You can still review the scene plan and generate the story.

​
Does the exported video include captions, music, or transitions?

No. The current beta exports the original voiceover with generated scene images and hard cuts. Captions and music are not burned into the MP4.