What problem does it solve? Creating talking-head videos, explainers, and presentations traditionally requires cameras, actors, and editing time. This Skill connects to the HeyGen API so you can generate AI avatar videos programmatically, from one-shot prompt-based generation to precise multi-scene productions with specific avatars, voices, backgrounds, and captions. ## Core Features & Use Cases - Prompt-Based Video Generation: Use the Video Agent API to turn a structured text prompt into a complete video, with guidance on writing production-quality prompts using named visual styles and scene-by-scene breakdowns. - Precise Avatar Control: Build videos with the v2 API by selecting specific avatars, voices, scripts, backgrounds, text overlays, and per-scene timing. - Photo Avatars & Assets: Upload images to create talking-photo avatars, generate AI photo avatars from text descriptions, and manage custom media assets. - Use Case: A marketing team needs a 90-second monthly metrics report video. The Skill guides prompt writing with the Swiss Pulse visual style, generates the video via the Video Agent endpoint, then polls the status endpoint to retrieve the download URL. ## Quick Start Ask the AI to generate a HeyGen video from a short brief, for example: create a 60-second landscape video with a professional avatar announcing our product launch. Note: This Skill is marked deprecated in favor of the focused create-video and avatar-video skills, but remains functional for backward compatibility.
