The Fast One

A clay stop-motion short made by Clayvoyant from two scene files and one page of character descriptions. Nobody opened Blender, drew anything or recorded a voice.

Seventeen filmed shots, thirteen voiced lines. Made with sastudio film examples/the-fast-one --preset preview in 55 minutes on a laptop GeForce GTX 1660 Ti.

Where Clayvoyant began

I first made a 29-minute clay stop-motion film to teach information security at my father's workplace. It was hard to build: I had to join many tools together, work around the limits of my hardware, and write my own pipeline to sculpt, animate, voice, light and film every scene.

Nobody making an awareness or classroom film should have to rebuild all of that, or spend a paid video-generation quota on every scene. So I turned what I built into Clayvoyant and made it open source. You write the people, their lines and the places in a few text files; it sculpts the cast, builds the set, directs the cameras, voices the lines and puts the film together on your own computer.

It still needs Python, FFmpeg and, for clay, Blender, and rendering takes time: The Fast One took 55 minutes on a laptop graphics card. What it saves you is the patchwork of tools, and with the free voices there is nothing to pay per film.

The original film, complete: 28 minutes 51 seconds. Watch on X
What went into the original, and what Clayvoyant does now

The original: Blender for the clay; Remotion and FFmpeg for compositing and the edit; Sarvam Bulbul and ElevenLabs for the voices; Mixkit music and sound effects; Poly Haven models and textures and Pexels footage for the rain; lettering from an alphabet I drew in code; Earshot to check the sound; and AI-assisted engineering throughout. I also tried Tripo3D and BlenderKit for models, but neither made it into the final film.

Clayvoyant:

What changed, frame by frame

Each pair is two real renders of the same moment: on the left before a fix, on the right after it.

Left: Tara stands square to the camera while Bashir talks to her. Right: the same frame after the fix, Tara turned towards Bashir.
People turn to the person they talk to. Every standing spot used to pin a body to the lens.
Left: the speaker cut in half by the left edge of a wide shot. Right: the same wide with her fully inside the frame.
Everyone a shot is on stays inside the frame: heads are projected through the real lens.
Left: an over-the-shoulder shot that shows the back of the speaker's head. Right: the same line filmed from the front, her face and her phone visible.
No shot shows the back of a speaker's head.
Left: Odile speaking behind the counter. Right: the cut to Tara listening while Odile's line continues.
A long line cuts to the listener between two words, where the speaker's mouth rests.

Things a scene file can ask for

Left: a close-up under the preset light. Right: the same close-up with a low warm key from the other side.
direction.light: the preset on the left, a low warm key from camera right on the right.
A home office: Bashir's laptop is open at the start of the shot and closed at the end.
direction.props: Bashir's laptop closes as Tara arrives.
Left: steam rising off a mug on a cafe table. Right: a wall clock reading five past seven.
direction.dressing: [steam] and direction.clock: "07:05".