What problem does it solve? Creating presenter-style videos, lip-synced footage, or clean background-free cutouts normally requires video editing software and manual work. This Skill lets an AI agent call the Veed API through the Pixazo gateway to produce these videos programmatically from an image, audio track, or source video. ## Core Features & Use Cases - Talking Avatar Generation: Combine a reference image and an audio track into a speaking-presenter video with Veed Fabric 1.0. - Lip Sync: Match a speaker's lips in an existing video to a new audio track using Veed Lipsync or Lipsync 2.0. - Video Background Removal: Strip the background from a video clip for clean cutouts. - Use Case: A marketer has a product photo and a recorded voiceover; the agent submits both to Veed Fabric, polls the async task until complete, and returns a ready-to-share talking-avatar video URL. ## Quick Start Ask the agent to create a talking-avatar video from a portrait image and an MP3 voiceover using Veed, providing your Pixazo API key when prompted.