# Photo Video Create AI scene images for your song, choose captions and a waveform, and review the price before rendering a Photo Video. > Canonical: https://aimusicis.com/ai-music-video/photo-video ## Three Photo Video renders, ready to watch Every clip below came out of this tool's own visualizer renderer, using one of the page's reference tracks. Each is a 45-second 720p excerpt with the title, artist and waveform on; captions stay off because none of these tracks has timed lyrics. ### New Jack Swing Rendered with the Spectrum Bars template as a 45-second 720p excerpt, waveform on and captions off. ### Noir Saxophone Rendered with the Pulse Ring template as a 45-second 720p excerpt, waveform on and captions off. ### Battle at the Bridge Rendered with the Wave Line template as a 45-second 720p excerpt, waveform on and captions off. ## Photo Video gives your song a visual sequence ### Images shaped by your song The workflow transcribes the audio and plans original scene images from its lyrics and your selected visual style. One image can hold throughout the song, or multiple images can form a sequence. ### Captions and a moving waveform Place captions at the top, middle or bottom and decide whether to include the audio waveform. The preview checks timing and placement; the generated images arrive with the finished video. ## Create a Photo Video from an audio track ### Choose the audio Upload a supported audio file or select an owned track from My Music. Audio stays attached to the saved project used for generation. ### Choose the visual treatment Select single or multiple images, a landscape or portrait canvas, and a photo style. Set caption placement and turn the waveform on or off. ### Review the quote and generate Check the credit quote before submitting. My videos shows the task and its finished MP4; an unconfirmed submission can be retried with its original settings. ## Photo Video input and output limits ### 2 aspect ratios Choose 16:9 landscape or 9:16 portrait. ### 32 scene images The upper limit for multiple-image generation; single-image mode uses one. ### 15 minutes of audio Upload one supported track, up to 50 MB. ### 1 MP4 export Download the finished video from My videos. ## Photo Video features Photo Video combines automatic transcription, scene-image planning and MP4 rendering in one task. The displayed quote covers its generation stages. ### A coherent visual treatment Choose from 28 photo styles, including cinematic film stills, analog photography, ink illustration and stylized animation. The planner uses the selected treatment across the scene sequence. ### Landscape and portrait canvases Choose 16:9 for a horizontal video or 9:16 for a vertical release. The selected canvas applies to the generated scene images and final MP4. ## Who creates a song-led Photo Video ### Independent musicians Give an original song a visual release without arranging a photo shoot. ### Music storytellers Build a sequence of generated scenes around a song’s words and mood. ### Short-form creators Create a vertical music clip with captions positioned for the composition. ## Where Photo Video results go next ### [AI Music Generator](https://aimusicis.com/ai-music-generator) ### [AI Mastering](https://aimusicis.com/ai-mastering) ### [AI Music Visualizer](https://aimusicis.com/ai-music-visualizer/create) ### [Music Video: Visualizer](https://aimusicis.com/ai-music-video/music-visualizer) ### [AI Music Video](https://aimusicis.com/ai-music-video) ## Tools related to Photo Video ### [AI Music Video](https://aimusicis.com/ai-music-video) ### [Music Video Maker](https://aimusicis.com/music-video-maker) ### [Music Visualizer Templates](https://aimusicis.com/ai-music-video/music-visualizer) ### [Lyric Video Maker](https://aimusicis.com/lyric-video-maker) ## Photo Video questions Practical answers about audio inputs, generated scenes, captions and finished videos. ### What is Photo Video? Photo Video creates AI scene images from a song and combines them with audio, optional captions and a waveform into an MP4. ### Do I need to upload photographs? No photographs are required for this generator. Select a photo style and the task generates its scene images. Use the visualizer editor when you want to arrange your own existing pictures. ### How many scene images are generated? Single-image mode creates one image. Multiple-image mode chooses a count from the decoded audio duration, up to 32 images. The quote shows the count before you start. ### What aspect ratio should I choose? Choose 16:9 for a horizontal canvas or 9:16 for a vertical canvas. Both choices use the same audio input. ### How long can the audio be? The current limit is 15 minutes and 50 MB. Supported audio inputs include MP3, WAV, OGG, M4A, AAC and FLAC. ### Are the scene cuts matched to detected beats? Scene intervals cover the audio duration evenly. They are not currently placed at detected beats. The optional waveform reacts to the audio while the video plays. ### Can I use the Photo Video tool for commercial projects? Aimusicis does not currently issue a commercial-use license or certificate. Download access is separate from usage rights; review the current Terms and confirm you hold the rights to every uploaded or referenced source before publishing. ### What should I do after using the Photo Video tool? Open My videos to follow the task and download the finished MP4. The saved project retains the audio and generated image references for later editing. ### How many credits does Photo Video use? Photo Video draws between 29 and 91 credits per run, depending on the settings selected in the form. New accounts start with 10 free credits, and every plan and pack is priced in the same credits. ## Give your song a Photo Video Choose audio, select a visual treatment and review the generation price before starting. _Last updated August 28, 2026_