Generate videos with a single prompt. Describe what you want in plain text, and the agent handles avatar selection, scripting, scene composition - all in one.

fal-ai/heygen/v3/video-agent

Generate videos with a single prompt. Describe what you want in plain text, and the agent handles avatar selection, scripting, scene composition - all in one.

Inference

Commercial use

Partner

Schema

LLMs

Playground API Examples

SandboxOpen in Sandbox

Input

Prompt*

Create a 8-second explainer video about fal.ai Video Workflows. Target audience: Developers, AI engineers, and creative tech teams Brand colors: Teal, purple, and pink accents [0:00 – 0:02 | Hook] Hard cut in (no fade) + glitch hit Voiceover: “Most video models just generate clips—” On-screen text: “Just Clips?” → quick distortion + break apart [0:02 – 0:04 | Core Shift] Snap transition → node graph UI builds instantly Voiceover: “fal.ai runs the whole pipeline.” On-screen text: “Full Pipeline” (teal glow, expands) [0:04 – 0:07 | Feature Flash (Rapid Stack)] Instead of separate scenes → stacked rapid overlays (0.7s each) “⚡ Sub-second” “🔗 Chain models” “🎛️ LoRA ready” “🚀 API-first” Visual: Nodes connecting fast, code + UI elements flicker in sync

Additional Settings

Customize your input with more control.

Your request will cost $0.034 per second.

Result

Idle

What would you like to do next?

Download

Your request will cost $0.034 per second.

fal-ai/heygen/v3/video-agent, details and endpoints

fal-ai/heygen/v3/video-agent

Input

Result

What would you like to do next?