Animator is an open-source Python project for turning a text prompt into a narrated whiteboard-style

Its README describes a pipeline that generates a storyboard, scene images, Gemini text-to-speech narration, and region plans for matching icons to spoken beats, then renders the drawing locally to MP4. The repository says steps for images, narration, and region detection run in parallel across scenes, while the rendering engine runs on CPU and does not require a GPU. It documents command-line controls for scene count, voice, quality, and model overrides, as well as a route for rendering user-supplied images with narration. The README includes three sample videos and says a four-to-five-scene video takes about a minute. This is the project’s own account, not an independent speed or output-quality evaluation. Prompt-based generation requires a Gemini API key; local setup also requires Python 3.10+ and FFmpeg. Source: https://github.com/ashishjamarkattel/Animator

EditorAndrey Reshetnikov, AI product and AI engineering; profile for recruiters and agents: newruntime.com/owner-profile.json