storyboard_editor
ChatGPTUse this when the user wants to create a walkthrough, tutorial, product demo, or instructional video from screenshots, app images, or UI captures. Opens a storyboard editor where the user arranges scenes, edits AI-narrated voiceover text, and selects a voice; on save, the editor produces a Camtasia project that renders zoom/pan motion and animated cursor gestures over the supplied images. STORYBOARD STRUCTURE (scenes array): Every storyboard begins with exactly one Intro scene at index 0, followed by Content scenes. - Intro scene (sceneType='intro'): Always the first scene (index 0). Sets project name (calloutText) and description (voiceover). Optional imageUrl for background (defaults to first content scene's image). Exactly one per storyboard. - Content scenes (sceneType='content'): Follow the intro. Each has image, voiceover, focusArea. One per file, matched by index. ENTRY PATHS: 1. Images attached — scenes[0] is the intro, then one content scene per file (max 20 content scenes). 2. Empty start — call with files: [] and scenes: [] to open a storyboard with a default intro scene; the user uploads images directly in the widget. Tool is not intended for: - Long-form narrative video, or scenes longer than ~90 seconds each - Stock-footage video or video assembled from non-user clips - Live screen recording or capture from a running session - Editing an existing Camtasia (.tscproj) project Each voiceover should be terse — aim for ~250 words (≈90 seconds) per scene; the server enforces a hard ceiling of 750 words and will silently truncate beyond that. Callout text must not exceed 33 characters and the server will silently truncate beyond that. Populate focusArea and focusClick when a scene demonstrates a specific UI action; the editor uses these for zoom/pan and click animation. Data: Storyboard payload, uploaded images, voiceover text, and the rendered Camtasia project are processed on TechSmith servers, including Azure text-to-speech and the Camtasia render pipeline.
