Illustrated stories
Bring personal memories and original stories to life with a shared look for recurring characters, objects, and places.
YOUR VOICE. A WHOLE NEW PICTURE.
Audio SlidesNEW
Turn your audio into an illustrated video.
Your voice. Your story. Brought to life.
Upload a voice recording or record right here. AI turns your narration into a storyboard and creates images timed to your words. Choose a look, make it yours, and download your video.
Create a video →Up to 5 minutes of audio12 visual styles + your ownLandscape, portrait, or squareMP4 download
FROM VOICE NOTE TO VIDEO
How to turn audio into a video.
- 01
Start with your voice.
Bring an MP3, M4A, WAV, WebM, or OGG recording up to 5 minutes and 50 MB. Or hit record and talk. Pick a visual style and a landscape, portrait, or square format.
- 02
Make it feel like you.
AI plans scenes around the ideas in your narration. Review the transcript, edit the image descriptions, and choose optional captions before generating your images and video.
- 03
Watch it come together.
Download an MP4 with illustrated scenes timed to your original voice. Each still image stays on screen for its part of the story, with direct cuts between scenes.
A PICTURE FOR EVERY IDEA
An AI audio to video maker for your stories.
Give a voice note, narrated lesson, or spoken story a visual home. Audio Slides builds the pictures around what you say, so you can make a video without filming yourself.
Lessons and explainers
Turn a recorded explanation into a sequence of pictures. Edit each scene’s description to show the idea you want people to remember.
Shorts and social posts
Use portrait video for YouTube Shorts and Instagram Reels, square for feeds, or landscape for YouTube. Add captions to help viewers follow along.
Pick a world for your words.
12 WAYS TO TELL ITIllustration
Cinematic
Watercolor
Retro pixels
Clay
Miniature
Comic book
Line art
Paper cut
Anime
Oil painting
3D animation
Style inspiration. Audio Slides generates your images with FLUX.2 Klein 9B.
Audio Slides questions, answered.
Is Audio Slides free?
Yes. Your free account includes 40 credits each day, shared with the other AI tools. Each image created costs 1 credit, including visual references and regenerated images. Before creating your storyboard, we reserve up to 12 credits for recurring characters, objects, and places. Your story can have more than four references; each scene uses only the ones it needs, up to four. Unused credits are returned; you pay only for reference images that finish. A 10-scene video costs 10 credits for its scene images, plus the references created for your storyboard. Video creation and updates are included. You see the cost before generating. Credits reset at midnight UTC.
What audio files can I turn into a video?
Upload an MP3, M4A, WAV, WebM, or OGG file up to 50 MB and 5 minutes long, or record your voice in your browser. Audio Slides works from spoken narration, such as a voice note, a story, or an explanation. Your finished video downloads as an MP4.
What kind of video does it make?
An illustrated slideshow of still images timed to your original audio, with direct cuts between scenes. Each scene gets its own image in your chosen style. Use portrait for Shorts and Reels, landscape for YouTube, or square for a feed.
Can I change the storyboard?
Yes. Correct the transcript for each scene, edit what its image should show, split a scene, or merge it with the next one. Transcript corrections update the displayed words and captions; your original recorded audio stays the same.
Can I add captions to my video?
Yes. Choose a caption style while reviewing your storyboard, or leave captions off. You can correct the transcript before generating and download a separate SRT caption file with your finished video.
How long are my files saved?
Your projects and files are automatically deleted 24 hours after upload starts. Download your finished MP4 before the deadline shown in your project. Find unfinished projects in My work.
Will every character look exactly the same?
The storyboard creates shared visual references for recurring characters, objects, and places. Review these before generating your video. Scene images use the relevant references to carry appearances through the story while changing the action and composition. AI-generated details can still vary. Review the finished video before sharing it.
Your next video starts with your voice.
Bring a recording. Give it a look. Tell your story.