gator/paytolaugh
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
PayToLaugh - upload your pet, pick a topic, get a video of them weighing in
56 commits 1 branch 0 tags 4.2 MiB
HTML 96.6%
JavaScript 2.1%
CSS 1.3%
Find a file
gator 4d553585d6 Cut the shots where the clock says, not where a word count guesses 
"I am not" and "extraordinarily unimpressed" are both three words and nowhere
near the same length, so any word budget is a guess about something we can
measure. Three attempts at tuning one were wrong in both directions.

Speaking the monologue once returns the start and end of every character, so
word boundaries are exact. This cuts each shot at the word whose end sits
nearest the boundary, preferring a sentence ending when one is close. On the
first real test it produced a 20 word shot landing at 7.8s and cutting on a
full stop, where the budget had said 18.
2026-09-08 14:46:15 +00:00
assets Session tokens, server-driven menu, and times on My videos 2026-09-07 12:38:56 +00:00
admin.html Do not call a continuation shot's missing frame a fault 2026-09-07 17:50:25 +00:00
create.html Wire the collateral step 2026-09-07 21:16:16 +00:00
index.html Add My pets to the home page nav 2026-09-05 14:09:33 +00:00
pets.html Put the big rough voices at the top of the list 2026-09-08 03:18:22 +00:00
README.md Demo page: Veo 3.1 Lite talking-dog clip with generation notes 2026-09-04 17:43:36 +00:00
register.html Store the session token issued at sign in 2026-09-07 12:39:36 +00:00
script.html Cut the shots where the clock says, not where a word count guesses 2026-09-08 14:46:15 +00:00
videos.html Add an Edit button beside Download on a finished video 2026-09-07 21:14:47 +00:00

README.md

paytolaugh

Demo page for PayToLaugh — upload a pet photo, pick a topic, add director notes, get a short video of the pet weighing in.

Deployed static to paytolaugh.corben.ai.

Contents

  • index.html — single-page demo. Embeds one generated clip plus notes on how it was produced, the pipeline findings, and the known rough edges.

The embedded clip

google/veo-3.1-lite via the OpenRouter video API. Text-to-video with native audio, 8s, 720x1280, 24fps. No reference image and no separate lip-sync pass — the dog, the speech and the mouth movement come out of one generation.

Hosted at https://api.corben.world/files/00eb3251-8257-4bfd-a164-fb9ea76aa8b3/public.

Deploy

Static mode, index.html at the repo root.