Technical demo

Your pet has opinions.

Upload a photo, pick something being argued about online, add your own director notes — and get a short video of your pet weighing in. This page documents how it is built.

Dog-In Podcast — the full cut

720×1280 · 40s · h264 + AAC · 7.2 MB

Four dogs, one argument

Everyone stays on screen the whole time, like a real call. The audio runs in sequence so only one speaks at a time, and the live tile carries a lit border. Each dog was generated alone, then composited — asking one model for four characters in a single shot produced the same dog four times.

Butcheroverclaims the market
The Goldenreframes it as displacement
Marshallthe bleak second-order note
Moosedisputes the number

One character, on its own

720×1280 · 8s · 3.3 MB

Butcher, on humanoid robots

The dog, the speech and the mouth movement all come out of a single text prompt — no reference photo and no separate lip-sync pass. This is the unit the grid is built from.

Model	google/veo-3.1-lite
Route	OpenRouter video API
Mode	Text-to-video, native audio
Generation time	62 seconds
List price	$0.05 / second at 720p

How it is made

The photo

Breed, coat colour and markings are described in words. Naming the breed explicitly carries the likeness further than image resolution does.

The topic

A real discussion — a thread, a podcast clip, an argument. The claim being made is preserved; only the stakes change.

Director notes

The owner supplies the attitude. Loud and self-important, or flat and unimpressed. This is what makes it sound like their pet.

The render

Each character is generated alone, then the four are composited into one grid with captions and branding.

Notes from the build

Native generation beats lip-sync retrofitting. Post-hoc lip-sync tools are trained on human faces and track landmarks a muzzle does not have. Generating the animal already talking sidesteps the problem — the single most important finding so far.
Composite, do not ask for a crowd. Prompting one model for four characters on a call rendered the same dog in every panel. Four separate generations tiled in post gives four genuinely distinct dogs and exact control.
Describing the breed matters more than image quality. A full-resolution character plate was reconstructed faithfully from a 150×150 thumbnail once the coat and markings were named in words.
Every line is verified, not assumed. Generated audio is transcribed back with Whisper and checked against the script before a clip is accepted.
Each shot gets a clean context. Generating several clips in one conversation caused dialogue to bleed between characters — one had another’s line appended to its own.
Video needs remuxing before it will play in a page. Model output puts the moov index at the end of the file, so a browser shows a blank player until the whole thing downloads. A lossless faststart pass moves it to the front.
Captions are burned in afterwards, not generated. Video models render text unreliably; an overlay pass gives identical typography across every clip and costs nothing to restyle.

Known rough edges

Honest first pass, not a finished result. Moose’s line picked up a fragment of Butcher’s and needs regenerating in a clean context. The laptops still visible in each room are leftovers from an earlier approach and come out of the prompt next. Butcher’s coat also drifted tan-heavy on the single-shot version where the character is meant to be predominantly white.