# Notes on the Fameo three-step workflow (step by step) This is a short, practical write-up rather than a review. Every claim below comes from the tool's own pages. Personal notes after making a series of short talking clips with [make a photo talk](https://fameo.ai). The product is an AI lip-sync talking-video generator. The published steps are: 1. **Choose or upload** — start from a template or add your own photo or short video. 2. **Script the moment** — type text or add your own audio. 3. **Share the result** — create a talking video in minutes and export in HD. Clear, front-facing images usually work best. Portraits, pets, cartoons, and artwork are all supported when the face is visible. Most videos come back within a few minutes, depending on queue time, duration, and content type. When I need a specialized input I leave the general page and use the matching tool, for example the [photo singing tool](https://fameo.ai/lip-sync-generators/ai-photo-sing) for a song, or mimic motion when I want body movement rather than speech. I only use authorized media. Questions about the product go to support@fameo.ai. Start with a ten-second test clip, then adjust the image or the script rather than the length.