Avatar model · by ByteDance

OmniHuman 1.5lifelike avatars

ByteDance's OmniHuman 1.5 is the maximum-realism avatar tier in Shorz — for presenter videos where the performance has to pass as filmed.

  • Max realism
  • From 25 credits per second
  • Tier · Premium
  • Motion prompt · No

Made with OmniHuman 1.5 in Shorz

Real clips generated in Shorz from one photo and a voiced script, unedited. Press play for sound.

6s · photo + voice (Jessica)

Script: “Golden hour is my favourite time of day. Everything feels a little softer, doesn't it?”

OmniHuman 1.5 at a glance

OmniHuman 1.5 is ByteDance's human-animation model. Instead of a motion prompt, it reads the voice track itself and generates the performance from it — expression, emphasis and movement — which is why it's the most realistic option in Shorz and the most expensive per second.

Specs in Shorz

Made by
ByteDance
Version
Pinned to OmniHuman 1.5
Input
One presenter photo + generated or uploaded voice
Motion prompt
None — performance is driven by the audio
Used in
Avatar and Podcast projects
Billing
Per second of rendered avatar video
Failed generations
Never billed

Price in Shorz credits

25credits per second

1 credit = €0.01. Prepaid packs, no subscription, credits never expire. Prices are read from the same live catalog the app uses. See packs

Why pick OmniHuman 1.5 in Shorz

Maximum realism

The higher-quality tier for presenters who need to look filmed, not generated.

Audio-driven performance

Expression and movement follow the voice — no prompt to write.

Pinned version

Shorz pins OmniHuman to version 1.5, so a re-render matches the original.

Best for

  • Brand spokesperson videos
  • Ads
  • Premium courses
  • Close-up presenters

How to use OmniHuman 1.5 in Shorz

Shorz is a desktop app for Windows and Mac. Download it, sign in, and OmniHuman 1.5 is already in the model picker — no API key, no waitlist, no second subscription.

  1. 1Download Shorz for Windows or Mac and sign in.
  2. 2Start an Avatar or Podcast project.
  3. 3Upload a presenter photo or generate one, then write or generate the script.
  4. 4Pick the avatar model and a voice — Shorz voices the script with ElevenLabs.
  5. 5Render: the model animates the photo to the audio, then Shorz captions and finishes the video.

OmniHuman 1.5 vs other avatar models

All avatar models in Shorz, with live credit prices.

ModelBest atTierMotion promptCredits
Kling Avatar ProThe default talking-avatar model — Kling's Pro tier, with motion and gesture prompts.ProYes18 per second
Kling AvatarKling's standard avatar tier — half the per-second price of Pro, for drafts and long scripts.StandardYes9 per second
OmniHuman 1.5ByteDance's premium avatar model for the most realistic presenter performance.PremiumNo25 per second
HHeyGen Avatar IVHeyGen's Avatar IV lip-syncs any single-person photo — the lowest per-second avatar price in Shorz.BudgetNo5 per second

Every model, one app

Shorz isn't a model playground. The models generate the parts; the editor around them turns those parts into a finished, captioned, published video.

  • Every model on one prepaid balance — no per-provider subscriptions
  • No watermark on anything you generate or export
  • Full commercial rights on what you create
  • No API keys to manage: the models run on your Shorz account
  • New model versions appear in the picker without an app update
  • Drivable from Claude, Cursor, Codex or Gemini over MCP

OmniHuman 1.5 questions

OmniHuman 1.5 for maximum realism; Kling Avatar Pro (the default) for a lower per-second rate and gesture control through a motion prompt.

No — OmniHuman 1.5 has no prompt field. It derives the performance from the audio.

No. It runs on your Shorz account and bills per second in Shorz credits.

Still have questions? Ask founder