Shotcraft
Lip sync and avatars

HeyGen Avatar IV (and Avatar V)

Avatar IV is HeyGen's current default avatar engine, driving a photo, consented digital twin or studio avatar from either a typed script (text to speech) or an uploaded audio file, analysing vocal tone and rhythm to generate matching facial motion.

A lip sync and avatar tool by HeyGen · read 2026-08-14 · sourcing high

Up to
3600 seconds
Resolution
3840x2160
Weights
Not released
API
Yes
Commercial use
Permitted subject to conditions

It also handles non-human, cartoon and 3D-model avatars. Avatar V is the higher-fidelity tier and is restricted to consented Digital Twin avatars.

Commercial use — Permitted subject to conditions

Users retain ownership of avatars they create but must hold the legal rights and explicit consent for any real person's likeness and must honour removal requests.

  • Requires consent from the person depicted. Consent is mandatory for digital twin avatars: the person depicted must complete HeyGen's consent verification confirming identity and authorising creation of their likeness, and consent is tiered with higher levels unlocked for narrower sets of accounts

The conditions above were extracted from the licence notes recorded during research, and each one shows the sentence it came from so you can check the reading. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from HeyGen's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is strong: the figures came from pages we retrieved and read. Check the vendor's current documentation

What it takes in
image, text, audio
What it makes
video
Maximum duration
3600 seconds
Maximum resolution
3840x2160
Aspect ratios
not established
Controls
avatar-from-photo, avatar-from-video, lipsync, voice-clone
Weights
Not released
API
Yes
Pricing
Subscription plus pay-as-you-go API. Plans: Free $0 (3 videos/mo, 1 min max, 1080p), Creator $29/mo (600 credits, 30 min max, 1080p), Pro $49/mo (1,000 credits, 30 min max, 4K), Business $149/mo plus $20/seat (1,500 credits, 60 min max, 4K, 5 custom avatars), Enterprise custom (unlimited length). Credit rates: Avatar III 3 credits/min, Avatar IV and V 20 credits/min, Video Agent 20 credits/min. API is prepaid wallet: Avatar IV photo avatar $0.05/sec, Avatar IV digital twin and studio avatar $0.0667/sec, Avatar V digital twin $0.0667/sec, Avatar III digital twin and studio avatar $0.0167/sec, Avatar III photo avatar $0.0433/sec, photo avatar creation $1.00 per call. API rates are the same for 720p and 1080p.
Released or updated
not established

Supported aspect ratios is not established here. That means no page we could retrieve stated it, not that the model lacks one.

Strengths

  • Explicit, documented per-second API pricing across three avatar generations
  • Formal consent verification flow rather than a checkbox
  • 4K output on Pro and above; 60-minute videos on Business

Weaknesses

  • Avatar IV and V burn 20 credits per minute versus 3 for Avatar III, so plan credits go quickly
  • API is not available on Creator or Pro subscription tiers; it is a separate prepaid wallet
  • HeyGen's own help centre notes Avatar IV is particularly effective for non-human and stylised avatars, which hints at limits on photoreal human work
  • Aspect ratio support not published

Best for

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

MCP servers that front HeyGen

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Flawless DeepEditor and TrueSync

Neural performance editing tools for film and episodic post. DeepEditor applies new dialogue to existing shots and refines performances, covering in-v

Lip sync and avatars

Hedra character / avatar platform

Character and avatar video platform that has grown into a unified inference API putting multiple leading image, video and audio models behind one API

Lip sync and avatars

LatentSync

Open-weights end-to-end lipsync method built on audio-conditioned latent diffusion, generating mouth movement directly from audio without an intermedi

Lip sync and avatars

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.