HeyGen Avatar 6 Identity to Video

Lip-synced talking-avatar videos from a typed script.

Playground
APIPricing
~82.66s
Loading outputExample output
Try an example3

HeyGen Avatar 6 Identity to Video (Text-to-Video)

What is HeyGen Avatar 6 Identity to Video?

HeyGen Avatar 6 Identity to Video turns a typed script into a video of a ready-made HeyGen presenter speaking it. You choose one of HeyGen's public avatar looks by its look ID, type your script (or supply speech audio to lip-sync), and optionally pick a HeyGen stock voice and speaking speed. The model renders a photorealistic presenter who performs the words, in 1080p or 2K, in the aspect ratio you need. It is built for straight-to-camera presenter video — explainers, lessons, updates and ads — without a camera, studio or on-camera talent.

Key Features

  • Script-to-video from a public HeyGen avatar look, with no footage to shoot.
  • Context-aware gestures: the avatar points, counts and emphasizes in step with the words.
  • Fresh, varied motion on every line instead of one replayed loop.
  • Lifelike lip sync and a large step up in realism over earlier HeyGen avatars, up to native 2K.
  • Script up to 5,000 characters, or supplied speech audio — one or the other.
  • Optional HeyGen stock voice, adjustable voice speed, motion prompt and motion-expressiveness controls.
  • Standard or faster turbo tier; 16:9, 9:16, 1:1, 4:5, 5:4 or auto; no fixed length limit.

Best Use Cases

Product and feature explainers, course and training lessons, onboarding and help content, social reads and ads, and internal updates. Vertical 9:16 suits Shorts, Reels and TikTok; 16:9 suits courses and landing pages; 1:1 and 4:5 fit social feeds. Localize one script across different stock voices to reach new audiences, and batch many short clips from a single look.

Prompt Tips and Output Quality

Write the script the way you want it performed — the model reads meaning from the words, so a line that counts ("first… second… third") or points ("over here") produces matching gestures. Keep scripts tight, since the clip runs as long as the speech. Add a motion prompt for a specific gesture or expression, and set motion expressiveness to "less" for calmer, corporate delivery. In testing, a standard-tier 1080p studio-layout explainer produced a clean, photorealistic presenter with synced lips and varied, on-topic gestures.