Wisaven

Photo to video

Image to video with voiceover, captions and music

Write what should be said and describe how the picture should move. The photo is animated, your script is read over it, captions are burned in sentence by sentence and quiet music sits underneath. If the voice runs longer than the 10-second clip, the clip loops instead of cutting the voice off.

What you get

  • Video with voiceover, captions and music
  • Voiceover on its own

185 credits per run

The photo we started from (itself AI-generated for this demo)
13 seconds: the 10-second clip loops under the voice, captions and music added
A clear photo; it becomes the first frame

Free to try — sign in when you generate.

How it works

  1. 1
    Upload a photo and write the script
  2. 2
    Pick a voice, music and caption style
  3. 3
    Download the finished video

A real run

Made with this page and not retouched — what went in comes first.

The photo we started from (itself AI-generated for this demo)
The photo we started from (itself AI-generated for this demo)
Six a.m. at the lake. No phones, no noise. Just the water, the mountains, and a red canoe waiting for us. We paddled out before the wind came up. The whole valley was still asleep, and for an hour, it felt like ours.
Script · motion: “soft ripples on the water, the canoe drifting slightly, camera almost still” · voice Ethan · calm piano · bold captions
13 seconds: the 10-second clip loops under the voice, captions and music added

FAQ

How long can the script be?

Up to 30 seconds of speech — about 75 English words or 120 Chinese characters. The form shows roughly how long it takes to say. The picture is a 10-second clip; a longer voice plays over it looping.

Can I turn the captions off?

Yes — choose “No captions”. Otherwise the script is burned into the picture one sentence at a time, timed to the voice.

Which languages and voices?

Chinese, English, Japanese, Korean, Spanish, French and German (or Auto), with four voices.

Can I use the results commercially?

Yes, on every plan, the free one included — what you make is yours, subject to the Terms and to the rights in what you upload.

Is it free to try?

Yes — new accounts get free credits. Generating signs you in; paid plans add more monthly credits.

Need just one step?

🎞️ AI Image to Video🎙️ AI Text to Speech

More use cases

All use cases →
Add a voiceover to your videoUpload your own clip and a script: an AI voice reads it, captions are burned in sentence by sentence and music sits underneath. A short clip loops under a longer voice.Talking photoMake a portrait photo talk: type a line, pick a voice, get a lip-synced video up to 10 seconds long. Use your own photo, or one you have permission to use.Photo to video with musicBring a photo to life as a 5-second video with an original instrumental written for it — describe how the picture moves and what the music should feel like.Music video from your songUpload a song and describe the look: three cinematic shots are generated — wide, moving, close-up — cut together and set to your track as a 15-second music video.Faceless short video from a topicType a topic and get a vertical short with nobody on camera: a 30-second script written for speaking, an opening scene, an AI voice, captions and music — ready for Shorts, Reels and TikTok.Product ad video with a voiceoverOne product photo becomes a vertical ad for TikTok, Reels and Shorts: a studio shot, a slow turntable clip, a 15-second script written only from the facts you give, read by an AI voice, with captions and music.