Video module

Nine ways to make a video, one wallet.

Talking presenters, UGC ads, explainers, and full prompt-to-film movie making — on 8 models you pick per shot, 1 of which run on our own GPUs.

What's inside

AI Presenter
A consistent person talking to camera across a whole series — same face, same wardrobe, same set, beat after beat.
Social Ads
Product in hand, first-person script, shot like a creator filmed it rather than like an agency did.
AI Movie Maker
Prompt to storyboard to a finished cut — scenes, voiceover, and a music bed generated and stitched into one video.
Short Film
Start frame and end frame, and the model fills the motion between them. Long cuts assemble from shots.
Explainer
A narrated walkthrough with a presenter and reference imagery, for the video a support page can't replace.
Ad Remake
Feed in an ad that already works and rebuild it with your product and your presenter.
Sync Motion
Take a motion reference and put your subject in it, keeping the original sound if you want it.
Brand Story
Longer-form brand narrative with your name and palette carried through every shot.
Music Video
Upload a track and cut visuals to it — no voice script, the song is the script.

Pick your model per shot

The same panel offers a frontier model and a low-cost lane side by side, so one project can spend where it matters and save where it doesn't.

Veo 3.1

Google DeepMind

Google's flagship text-to-video and image-to-video model with native synced audio.

24 credits / sec (Fast) · 36 credits / sec (Pro) — an 8s clip is 192 / 288 credits

Kling 3.0

Kuaishou Technology

Kuaishou's flagship video model with native multi-lingual audio, in-video editing, and clips up to native 4K.

48 credits / sec (Kling 3.0/o3) — an 8s clip is 384 credits

Hailuo 2.3

MiniMax

MiniMax's Hailuo 2.3 delivers high-motion, physics-aware video clips with subject reference and flat per-clip billing.

16 credits / sec (flat — always billed at max clip length)

Seedance 2.0

ByteDance / BytePlus

ByteDance's default AutorunX video engine for Short Film, Movie Maker, and Ad Remake — identity-preserving reference-to-video at up to 4K.

97 credits / sec (Fast, Short Film/Movie Maker default) · 120 credits / sec (2.0/Identity, Ad Remake/Sync Motion default)

OmniHuman 1.5

ByteDance

ByteDance's audio-driven human video model that animates a photo to speak and move in sync with a given audio track.

101 credits / sec (Music Video/Explainer/Brand Story default)

Wan

AutorunX owned

Alibaba's open Wan model family, run two ways on AutorunX: self-hosted Wan 2.2 for cost-efficient generation, and cloud Wan 3.0 for up to 30-second clips.

2 credits / sec (owned Wan 2.2) · 45 credits / sec (cloud Wan 3.0 @ 720p)

Grok Imagine Video

xAI

xAI's image-to-video model that brings a still image to life with realistic motion over 30-second clips.

8 credits / sec

Happy Horse

Alibaba

An Alibaba-built image-to-video model offering 15-second clips at up to 1080p, available on AutorunX.

75 credits / sec

Make the first one today.

300 credits a month on the free plan — enough for a first presenter clip and a couple of re-rolls.