heygen-avatar-video
HeyGen avatar video production
Use this skill when the production path is HeyGen and the deliverable involves an AI presenter, digital twin, photo avatar, studio avatar, prompt-composed avatar clip, or real-time streaming avatar. Treat HeyGen as both a creative video tool and a likeness-handling system: lock consent, identity rights, script intent, voice rights, and output custody before generation.
Facts below were verified from official HeyGen documentation and policy pages on 2026-07-10. Recheck the linked docs for volatile fields such as prices, engine support, endpoint shapes, limits, status values, moderation policy, and plan entitlements before a paid run.
Choose the right HeyGen route
Prefer the most controllable API that still fits the brief.
- Use Video Agent (
POST /v3/video-agents) when the user wants a complete avatar video from a natural-language brief and accepts HeyGen choosing or composing the script, avatar, voice, and visual style. It is the fastest exploration path and supports one-shot generation or interactive chat-style iteration, but it gives less deterministic scene control. - Use Direct Video (
POST /v3/videos,type: "avatar") when the script, avatar look, voice, aspect ratio, background, captions, watermark, output format, or motion prompt must be explicit and repeatable. This is the default for production pipelines, personalized campaigns, compliance-reviewed scripts, and brand-controlled spokesperson videos. - Use Cinematic Avatar (
POST /v3/videos,type: "cinematic_avatar") only when the output is a short prompt-composed cinematic shot with 1-3 avatar looks and no spoken script. Do not choose it for normal talking-head narration. - Use Avatar Realtime (
POST /v3/avatar-realtime) when the user needs a live HLS stream of an avatar speaking in real time. It is for kiosks, live agents, assistants, and broadcasts where the application owns STT/LLM orchestration. It is not a rendered MP4 workflow. - Use Video Translation or Lipsync APIs for post-hoc localization or replacing audio on existing footage rather than regenerating the whole video when the visual source must be preserved.
Official routing basis: HeyGen's "Choosing the Right Video API" docs distinguish Video Agent as prompt-driven/low-control, Direct Video as structured/high-control, and Cinematic Avatar as prompt + avatar looks with no spoken voice. Official Avatar Realtime docs describe the real-time HLS path as separate from rendered video.