MakeThisVid generates 8-second video clips with AI-generated audio included — atmospheric sound that accompanies the visual. There is no silent mode. For spoken voice-over narration, add your own audio track in a video editor after downloading. Commercial use licensed on every plan.

AI Voice-Over Video Maker: Video with AI-Generated Audio

Every MakeThisVid video is generated with audio — there is no silent mode. Our AI creates atmospheric sound alongside the visual: environmental ambience, movement audio, and scene-appropriate sonic atmosphere. If you want a video with a specific narrated voice-over, the workflow is: generate the visual from MakeThisVid, record or generate your narration, and layer the voice-over on top in your video editor. The AI provides the visual and a foundation of audio — you add the words.

How to Use MakeThisVid

From prompt to downloadable MP4, ready to deploy.

  1. Write a visual prompt or use a photo

    Describe the scene you want to see (JPG/PNG/WebP optional, max 10 MB). Focus the prompt on the visual — the audio will be generated to match the scene automatically.

  2. Choose your mode

    Text → Video or Photo → Video. Both modes generate video with audio automatically. There is no audio-off option — every render includes AI-generated audio.

  3. Generate at 720p or 1080p

    1 credit per 720p video, 2 credits per 1080p. Most renders complete in 45–90 seconds. Credits refund automatically on failure. The downloaded MP4 includes audio.

  4. Add your own voice-over in your editor

    Download the MP4. Open it in a video editor (CapCut, DaVinci Resolve, Premiere, iMovie). Add your narration audio track on a separate layer — mute or replace the AI audio as needed. Export with your voice-over.

  5. Publish your voice-over video

    Commercial use is included on every plan. Use the video with your narration in ads, social content, presentations, or any commercial use.

Who Uses MakeThisVid for This

Brand video narration

Generate a cinematic visual background and overlay a narrated brand story. The visual sets the mood; the narration delivers the message. Combine in any video editor.

Tutorial and explainer content

Generate an atmospheric visual backdrop for a screen-free explainer — the visuals communicate the context while the narration explains the concept or product.

Social media video with caption audio

Generate the visual, record your talking points, and layer them over the atmospheric video as a voice-over track. A content format that performs well on Instagram, TikTok, and YouTube.

Frequently Asked Questions

No. MakeThisVid generates AI-created atmospheric audio that matches the visual scene. It does not generate narrated speech or spoken voice-over. For narration, record or generate your voice-over separately and layer it onto the video in your editor.
Yes. There is no silent mode — every MakeThisVid video is generated with audio. The audio is AI-created atmospheric sound matched to the visual scene.
Yes. Download the MP4, import it into any video editor (CapCut, Premiere, DaVinci Resolve, iMovie), and add your narration audio track on a separate layer. You can mute the AI audio track and export with your voice-over only.
CapCut (free, mobile and desktop), iMovie (free, Mac), DaVinci Resolve (free), Adobe Premiere, and Canva Video all support adding audio tracks to imported video. The workflow is standard: import MP4, add audio layer, adjust timing, export.
Yes. Every plan and credit pack includes a commercial use license. Use the video with your voice-over in ads, social content, courses, or any commercial application.
From $0.40 per 720p on the Pro plan ($79.99/mo, 200 credits) to $0.75 on Lite ($14.99/mo, 20 credits). 1080p costs 2 credits. One-time packs start at $9.99 for 5 credits.
8 seconds, 720p or 1080p, 16:9 aspect ratio. Audio is always included. Renders complete in 45–90 seconds.

Generate your video with audio

Describe the scene or drop a photo. 45–90 seconds to a downloadable MP4 with audio — add your narration in any editor.

Try MakeThisVid