What problem does it solve? Producing talking-head videos, animated images, and dubbed content for social campaigns normally requires filming, actors, and manual translation. This Skill automates that production through HeyGen, turning scripts and images into finished presenter videos without a camera or studio. ## Core Features & Use Cases - Three generation modes: prompt-to-video via the Video Agent, explicit avatar plus script rendering, and image-to-video animation for key visuals or photos. - Multilingual dubbing: translate an existing video into other languages with create_video_translation, then poll until completion for reuse across markets. - Brand consistency: list and select avatars and voices by language and tone, then persist avatar_id and voice_id in smart-memory so every campaign video keeps the same presenter. - Use Case: A social media manager needs a 9:16 vertical video of a virtual presenter reading a campaign script in Portuguese. The Skill picks the saved brand avatar and voice, generates the video, polls until completion, and hands the MP4 to the ffmpeg post-production step for mandatory subtitles. ## Quick Start Ask the agent to generate a vertical HeyGen avatar video from the current campaign script using the saved brand avatar and voice, then add subtitles and export it for social publishing.
