发现优质的 AI Agent 技能

This file defines reusable prompt blocks (for LLM use) to generate platform-specific captions + options from 1–9 images and a theme, plus mood-to-music hints.

Translate and dub existing videos into multiple languages, preserving lip-sync and natural speech patterns. Provide a video URL or HeyGen video ID — no need to create the video on HeyGen first.

Webhooks allow HeyGen to notify your application when events occur, such as video completion. This is more efficient than polling for status updates.

Named visual styles for Video Agent prompts. Each is inspired by a real graphic designer. Ordered by mood intensity.

HeyGen's Video Translation feature allows you to translate and dub existing videos into multiple languages, preserving lip-sync and natural speech patterns.

After generating a video, you need to poll for status until the video is complete. HeyGen processes videos asynchronously.

- [Video Output Formats](#video-output-formats) - [Basic Video Generation](#basic-video-generation) - [Request Fields](#request-fields) - [Video Configuration Options](#video-configuration-options) - [Multi-Scene Videos](#multi-scene-videos)

The Video Agent API generates complete videos from a single text prompt. Unlike the standard video generation API which requires detailed scene-by-scene configuration, Video Agent automatically handles script writing, avatar selection, visuals, voiceover, pacing, and captions.

Generate speech audio files from text using HeyGen's in-house Starfish TTS model. Use this for standalone audio generation — separate from video creation.

Add text overlays to your HeyGen videos for titles, captions, lower thirds, and other on-screen text elements.

HeyGen templates allow you to create reusable video structures with variable placeholders, enabling personalized video generation at scale.

Scripts for AI avatar videos have different requirements than scripts for human presenters. This guide covers best practices for writing scripts that sound natural and render well.