Talking portrait
A photo of a person speaking one written line, with room sound.
Image to Video AI with Audio: Photo to Sound Clip
Image to video AI with audio turns a still photo into a moving clip that comes back with sound, such as speech, effects or music, made in the same render. In Reviral's Cinema studio you upload the photo, pick a model that is not marked No sound, and an 8-second Veo 3.1 Fast clip with sound costs 106 credits (~$1.32).
No credit card required to try — sign in with email or Google.
- Silent models are marked No sound before you pay
- Veo 3.1 Fast (per second): 4, 6 or 8 seconds with sound
- Seedance 2.5: up to 30 photos and 10 audio files
- Wan 3.0: up to 10 photos plus your own audio
Photo-to-video models that make sound
Veo 3.1 Fast (per second) takes up to 2 photos and makes 4, 6 or 8-second clips with sound: 106 credits (~$1.32) for 8 seconds. Seedance 2.5 takes up to 30 photos and runs 4 to 30 seconds: 115 credits (~$1.43) for 5 seconds. Wan 3.0 takes up to 10 photos and runs 2 to 30 seconds: 99 credits (~$1.24) for 5 seconds. Wan 2.6 takes 1 photo: 83 credits (~$1.04) for 5 seconds. Kling V3 takes up to 4 photos in 16:9: 50 credits (~$0.62) for 5 seconds.
Veo 3.1 Lite, Veo 3.1 Fast (flat 8-second price), the Hailuo models and Kling 3.0 Turbo are marked No sound, so pick them only when you will add your own track.
Bring your own sound instead
If you already have the voice line or the song, Seedance 2.5 accepts up to 10 MP3 or WAV files of up to 50 MB each and can work from audio alone, and Wan 3.0 accepts up to 5 audio files alongside a photo or clip. The model then builds the motion around your sound instead of inventing one.
Writing the prompt for sound
Describe the sound the same way you describe the picture: who speaks and what they say in quotes, which effects happen when (a can opening, rain on glass), and whether music plays under it. Name the camera move and the length too, so the model paces both together.
Ways to use this tool
Product with sound effect
A product photo with the click, pour or fizz it makes.
Travel still to clip
A landscape photo with wind, waves or street noise.
Song-led visual
Your own track as reference audio with a photo of the artist.
How it works
Step 1
Open Cinema
The Try button opens the Cinema studio with Veo 3.1 Fast (per second) picked.
Step 2
Upload the photo
Add it as a reference picture; models show how many they take.
Step 3
Describe motion and sound
Write what moves, what is said and what is heard.
Step 4
Render
The price for the length and size shows before you press Generate.
Real examples
Click any example to play it. Every clip below is an existing Reviral render.
Cinema studio travel clip
Wan 3.0 fashion clip on a rooftop
What it costs
A 8-second Veo 3.1 Fast (per second) clip at 720p costs 106 credits (~$1.32).
Changing the video's length, media type, or resolution can change the final price.
Dollar figures use the $4.99 Mini Pack rate. Cached for up to 1 hour.
Frequently asked questions
- Is there a free image to video AI with audio?
- Reviral is free to start rather than free per clip: Sign-up gives 100 free credits with no card, and the exact charge shows before anything renders. A 5-second Wan 2.6 clip with sound costs 83 credits (~$1.04), so you can compare it with your free balance before rendering.
- Can AI turn a photo into a video with sound?
- Yes. Models that are not marked No sound return the clip with audio made in the same render. Veo 3.1 Fast (per second), Seedance 2.5, Wan 3.0, Wan 2.6 and Kling V3 all take a photo as the starting picture.
- Can I use my own audio with a photo?
- Yes. Seedance 2.5 takes up to 10 audio files and Wan 3.0 up to 5, together with your photo, and builds the motion around that sound.
More in AI Video Models
Compare closely related tools, or browse the complete AI Video Models topic hub.
Kapwing Image to Video: Prices and an OptionKapwing's published plan prices next to Reviral's per-clip image-to-video prices, no subscription needed.Synthetic AI Video: What It Is and the RulesVideo made by AI instead of a camera, what the labelling rules ask for, and how to make it.Cheap Image to Video AI: Live Prices Per ClipThree low-priced photo-to-video models, priced live per clip, with no subscription.AI Video Generator GitHub Repos, Side by SideFour open video models on GitHub with their licenses and GPU needs, read from each README.AI Video Generator From Audio: Song or Voice InUpload an MP3 or WAV and get moving pictures that follow it, with or without a photo.How to make a lip sync videoMouth and voice made together, step by step.Kapwing image to videoKapwing's plan prices next to Reviral's per-clip prices.Synthetic AI videoWhat synthetic video is and the labels it needs.OpenAI video generatorAI video models compared