Wisaven

Photo to video

Product ad video: your photo, a turntable clip and a voice that sells it

A shop-floor photo is enough. The product is placed on a clean studio backdrop, unchanged, and filmed turning slowly as the camera eases in. A short script is written from your facts — what it is for, two or three real details, a closing line — read in the voice you choose, burned in sentence by sentence as captions, with music underneath. Nothing is claimed that you did not type.

What you get

  • The ad, 9:16
  • Script
  • Studio shot
  • Voice track on its own

105 credits per run

The photo we started from (itself AI-generated for this demo)
25-second ad
The inputs of the run shown on this page. Change anything before you run.
Any photo where the whole product is visible and in focus — the background does not matter

Use your own voice · Describe a new voice

Usually ready in about 4 minutes · Free to try — sign in when you generate.

How it works

  1. 1
    Upload a product photo and type the facts
  2. 2
    Pick a voice, music and caption style
  3. 3
    Post the ad; the studio shot works as a listing image too

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)
Product: Fig & Cedar soy candle
Facts: hand-poured soy wax, cotton wick, 200 g amber glass jar with a bamboo lid, about 40 hours of burn time, made in small batches
Voice Serena · soft jazz · bold captions
What we typed
Made for slow evenings at home. Fig and Cedar is a hand-poured soy candle. It burns with a cotton wick. Each one is poured in small batches. It comes in a 200 gram amber glass jar. A bamboo lid keeps it covered. You get about 40 hours of burn time. Light it. Let the evening settle.
Script it wrote
25-second ad

Then, keep going

Photos for the same product: white background + lifestyle shot →Just the 5-second turntable clip, no voice →Listing copy: title, five bullets, description, keywords →Guide: showcase video or vertical ad — which, and how →

FAQ

Does the product stay the same?

The studio shot is made from your photo with instructions to keep the exact shape, colours, label and text; the clip is filmed from that shot. Look at the frames before posting — a wrong detail is a wrong ad.

Why does the clip loop?

The turntable clip is 5 seconds and the voice runs 15 to 25; the clip repeats under the voice rather than cutting the voice short. Keep the facts to three or four and the loop is barely noticed.

Can I use my own script?

Not on this page — the script is written from your facts so it fits the length. For your own words over this kind of clip, make the studio shot here, then use Add a voiceover to a video on the Product video from a photo result.

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 Text to Speech🎞️ AI Image to Video✂️ AI Background Remover

More use cases

All use cases →
Dub a video into another languageUpload a video and pick a language: what is said is transcribed (or pasted), translated to match the timing, read by an AI voice over the original background (music and room sound are kept), and burned in as captions. Seven languages, 13 credits.Photo to video with voiceoverAnimate a photo and narrate it in one go: an AI voiceover of your script, captions burned in and background music — up to 30 seconds, 7 languages, 4 preset voices or your own.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.Bring an old photo to lifeUpload a scanned old photo: it is repaired and, if you like, colourised, then the people in it gently come to life for five seconds — a breath, a blink, the start of a smile — with their faces kept exactly who they are.Property video from a listing photoOne listing photo becomes a short property video: a slow camera move through the room, a 15-second script written only from your listing facts, an AI voice, captions and quiet music — for Reels, a portal page or a WeChat group.Sticker pack: four expressionsOne photo of your pet or yourself becomes four die-cut stickers — happy, sleepy, surprised, in love — each a transparent PNG with a 512 × 512 copy for WhatsApp, Telegram and WeChat.