Image to Video with Sound

Happy Wan turns one photo into a 4, 6 or 8 second video with generated sound, in 720p or 1080p. The photo becomes the first frame; your prompt describes how things move and what you should hear. It runs on Google's Veo 3.1 Lite.

Image To Video With Sound, Step By Step

1. Open the generator and sign in with Google.
2. Choose Image to video and upload one JPG, PNG or WebP photo (up to 10 MB).
3. Describe the motion, one camera move and the sound, for example: "Waves roll in, her hair moves in the wind, slow push-in. Sound of surf and gulls."
4. Pick 4, 6 or 8 seconds, 720p or 1080p, and 16:9 or 9:16. "Match image" keeps the shape of your photo.
5. Click Generate video, then watch and download the MP4 from the page or from My videos.

Writing The Prompt

• Motion first. Say what moves: water, hair, smoke, a person turning their head, a car driving off.
• One camera move. Push-in, slow orbit, pan left or crane up. One is steadier than several.
• Sound in its own sentence. Rain on a window, café chatter, a crowd cheering, wind. Veo 3.1 Lite makes the audio in the same pass as the picture.
• Keep it to one action. For a longer story, make several clips and continue each one from the last frame of the previous clip.

What To Expect

The sound is generated to fit the scene; it is not a recording you upload, and how closely it matches varies from clip to clip. Faces and small text in the photo can change as they move. If a result fails, its credits are refunded automatically.

What It Costs

30 credits per video at 720p and 35 at 1080p, the same for 4, 6 or 8 seconds. The $9.90 Starter Pack (600 credits) covers about 20 videos at 720p. See pricing for packs and plans.