PhotoDesc
Audio-described videos from your photos. Built for galleries, archives, social media, and anyone who wants their images described aloud.
Requires an M-series Mac.
Loading latest version…The app is free. You bring your own Gemini API key for the AI descriptions and narration. A typical project runs well under a dollar.
How It Works
Drop in a photo or a whole folder of them. PhotoDesc looks at each image and writes a clear spoken description of what's in it. The people, the setting, the details a listener can't see. Then it turns the set into a narrated video.
Two Ways to Export
Per Image
Each photo becomes its own short video with its own narration. Good for posting one at a time.
Combined Sequence
All the photos play back to back as a single video, with optional dissolves between them.
Voices and Music
Choose from a range of natural AI voices, or use the built-in macOS voices for free. Add a background music track and it loops under the narration, fading in and ducking down whenever the voice speaks so the words always stay clear.
You Review Everything
Before anything gets rendered, you review every photo in a window that shows you a thumbnail of the image, the description the AI wrote, and the voice it'll be read in. Edit the wording, re-crop the frame, change the voice, or regenerate any of it. Nothing is final until you say so.
Requires an M-series Mac.