Turn images and voiceover into a video.
Turn a voiceover and your images into a video. Match visuals to the narration, review every scene, then export.
1. Build your story
Beta supports English narration up to 10 minutes. Upload up to 100 images, 15 MB each; voiceover up to 100 MB; 500 MB combined.
Sign in to create a video.
Once uploaded, processing continues on the server. You can return to this page later.
2. Review your scenes
No reliable automatic matches found
The voiceover may not match these images. We could not confidently match any sentence, so no automatic video is ready.
Choose a different voiceover, or choose and review the images manually.
MP4 includes your images and voiceover. Download the SRT separately to add captions in your editor.
↓ Download videoDownload captions (SRT)Choose an image for each sentence. Start times control when images change. The first scene starts at 0 seconds.
Recent Beta projects
How to make a video from images and voiceover
- Sign in, choose up to 100 images and add an English voiceover up to 10 minutes long.
- Use smart matching or keep upload order, then review and adjust the image chosen for each scene.
- Choose the format and 720p or 1080p quality, export the MP4 and download SRT separately if needed.
A practical example
Example: arrange illustrations around a narrated explainer, then replace any suggested image that does not fit the sentence.
Formats and things to check
Images can be JPG, PNG or WebP. Voiceover can be MP3, WAV, M4A, AAC, OGG or WebM. This Beta tool processes files on RapidCaption infrastructure and keeps them for six hours. Automatic matching may repeat or omit images and needs review. Captions are downloaded separately, not burned into this MP4.