Custom avatar maker
Record 15 seconds of yourself and get a custom avatar that looks, moves and sounds like you. Type a script, generate a polished video and never sit through another filming session.
Record 15 seconds of yourself and get a custom avatar that looks, moves and sounds like you. Type a script, generate a polished video and never sit through another filming session.
Key featuresHeyGen Custom Avatar features
One 15-second video, one digital twin
Upload a single 15-second clip and Avatar V builds a persistent personal avatar that maintains your face, voice and micro-expressions across wide, medium and close-up shots. Your identity stays consistent throughout 30-minute videos, so every custom avatar video feels like you. Agents use the same avatar as a real estate video maker for listing updates and client outreach.
Change outfits, backgrounds and camera angles without re-filming
Avatar V separates who you are from what you wear. Swap outfits, settings and camera angles, or apply a face swap in the editor without recording anything new. One recording session covers your product launch, quarterly business update and social clips, each styled for its channel and audience.
Your cloned voice in 177+ languages
Pair your twin with AI voice Cloning so the delivery sounds like you, not a stock narrator. Phoneme-level lip-sync keeps mouth movement accurate in 177+ languages and dialects, which means one script can reach every market without re-recording a line.
Direct gestures in plain English
Custom Motion lets you type directions just as a producer would give them: look at the camera, lean in, keep the energy low. The same custom avatar can deliver a measured executive update, a punchy social AI video ad, or a high-energy social cut from a single script, so the delivery matches your personality without needing to reshoot.
Cinematic scenes with your twin
Place your avatar in cinematic footage with Seedance 2.0, the only integration that applies the model to real, verified human faces. Physics-accurate motion and director-level camera control transform a simple webcam recording into polished brand films, ads and B-roll ready to publish.
Use cases
Filming trainers for every module holds up L&D schedules. Build each training video using your expert's custom avatar instead: update the script, regenerate the lesson and keep courses current without booking a single reshoot.
Creator-style ads need a constant stream of fresh faces and takes. Generate scroll-ready clips each day with your avatar in different outfits and settings, test hooks quickly and keep feeds active while competitors wait for shoots.
Generic outreach gets ignored. Send each prospect a video where your avatar greets them by name, without recording a thing, so you can deliver a personal touch at a scale no calendar could accommodate.
Localise avatar-led videos for international audiences without recording every language on camera. Generate translated versions using your custom avatar and voice options, while keeping the presenter consistent across regional training, marketing and product content.
Leaders set aside hours for every business message. A digital twin delivers weekly updates, all-hands recaps and investor notes in minutes, keeping communication regular while leaving the calendar clear for decision-making.
Course creators spend their weekends filming lessons. Enter modules into the AI video generator and your avatar teaches each one, allowing a solo educator to publish an entire curriculum without ever picking up a camera again.
How it worksHow the custom avatar maker works
Turn a phone recording into a finished custom avatar video in four easy steps, with most taking just minutes.
Film yourself on a mobile or webcam in a well-lit space. Speak naturally; your movements are learned from this clip.
Read a unique consent code on camera. This verifies your identity and prevents unauthorised avatar creation.
Choose outfits, backgrounds and camera angles. Add your cloned voice or select from more than 300 options. Prefer a photo-based talking avatar? Use HeyGen's AI Avatar Generator (https://www.heygen.com/avatars) to create one from a single front-facing photo.
Paste in a script, adjust the pacing and render. Download the finished video in HD or 4K, then publish it anywhere.
A custom AI avatar is a digital version of a real person used to generate new talking videos from a script. With HeyGen, you record reference footage and a consent video, then use the finished digital twin in new videos without having to film every script again.
For a more natural-looking custom avatar, the reference footage matters. Avatar V learns movement, gestures and natural expression from your recording, so use clear lighting, steady framing, eye contact and the kind of movement you want the avatar to reproduce in future videos.
For Avatar V, start with a 15-second reference video. Record in good lighting with your face clearly visible and use natural gestures and expression. The clip teaches Avatar V how you move and perform, while the separate consent video confirms permission to create the avatar.
HeyGen's custom avatar workflow combines a short Avatar V reference recording, consent, reusable digital-twin looks, voice options, and scripted video generation. You can change outfits, settings, and angles without re-recording the original Avatar V reference clip, which is useful for repeat video production.
Yes. HeyGen's Anton Voroniuk customer story reports 15.5 hours saved per week and 1M+ students reached. The story also reports video production at 40x lower cost, showing how a reusable digital twin can support high-volume educational content.
HeyGen currently offers a Free plan with one Custom Digital Twin. Paid plans add more video-generation capacity and features. Because pricing and avatar limits can change, check HeyGen's current pricing before choosing a plan.
Only with their on-camera consent. The person in the footage must record their own consent statement, which verification checks against the training clip. The finished avatar stays private to your account and is never added to any public library.
Yes. Your cloned voice carries into 177+ languages and dialects with phoneme-level lip-sync, so mouth movement matches each language instead of looking dubbed. Teams routinely localize one finished video into dozens of markets in an afternoon.
No studio is required for a standard custom avatar recording. A mobile phone or webcam can work. Record in a quiet, well-lit space with your face clearly visible, keep the camera steady, and follow the on-screen recording guidance for the avatar type you choose.
Minutes, not days. Processing typically completes within about 10 to 15 minutes of uploading your clip and consent code. Platforms that rely on studio pipelines quote 5 to 15 working days for the same deliverable.
Yes. You can turn PowerPoint slides into a narrated video, use your script or speaker notes for narration, and add an avatar to present the material without filming the presentation.
Explore more AI powered tools
Bring any photo to life with hyper‑realistic voice and movement using Avatar IV.
Transform your ideas into professional videos with AI.
