diff --git a/index.html b/index.html
index 2ea9588..2b4676e 100644
--- a/index.html
+++ b/index.html
@@ -31,10 +31,11 @@
.player{width:100%;aspect-ratio:9/16;border-radius:14px;border:1px solid var(--line);
background:#000;display:block}
.cap{font:12.5px/1.6 var(--mono);color:var(--muted);margin-top:12px}
- .cast{list-style:none;padding:0;margin:0 0 22px}
- .cast li{display:flex;gap:12px;padding:9px 0;border-bottom:1px solid var(--line);font-size:15px}
- .cast b{min-width:112px;color:var(--ink)}
- .cast span{color:var(--muted)}
+ .run{list-style:none;padding:0;margin:0 0 22px}
+ .run li{display:flex;gap:14px;padding:11px 0;border-bottom:1px solid var(--line);font-size:15px}
+ .run b{min-width:64px;color:var(--accent2);font-family:var(--mono);font-size:13px}
+ .run span{color:var(--muted)}
+ .run i{color:var(--ink);font-style:normal;font-weight:600}
.grid{display:grid;grid-template-columns:repeat(auto-fit,minmax(210px,1fr));gap:16px}
.card{background:var(--panel);border:1px solid var(--line);border-radius:12px;padding:20px}
.card .n{font:600 12px/1 var(--mono);color:var(--accent);letter-spacing:.1em;display:block;margin-bottom:10px}
@@ -61,24 +62,23 @@
- Dog-In Podcast — the full cut
+ Dog-In Podcast — full cut
-
720×1280 · 32s · h264 + AAC · 13 MB
+
720×1280 · 48s · h264 + AAC · 19 MB
-
Four dogs, one argument
-
Everyone stays on screen the whole time, like a real call. Each dog has two takes — a speaking one and an idle one — and only shows the speaking take during their own slot. The rest of the time they are listening, blinking, tilting their head, scratching an ear or yawning. The live tile carries a lit border.
-
- - Butcheroverclaims the market
- - The Goldenreframes it as displacement
- - Marshallthe bleak second-order note
- - Moosedisputes the number
+ Three segments, ten generated clips
+
+ - 0–8sCold open. Butcher alone, full frame.
+ - 8–16sRoll call. The grid assembles; three listen while one talks.
+ - 16–48sThe topic. Each dog takes a turn on the same argument.
+ The first two segments are fixed furniture — they carry over to every episode untouched. Only the third is written fresh, so a new short costs four generations rather than ten.
@@ -88,18 +88,16 @@
-
speaking · 8s · $0.40
+ src="https://api.corben.world/files/be1d916a-9fbf-4460-abf9-5497b470d63e/public">
+
speaking · 8s
-
idle B-roll · 8s · reusable forever
+ src="https://api.corben.world/files/3f7a93c8-d20e-4aec-a8f9-a3b35b538bf9/public">
+
idle B-roll · 8s · reused every episode
- The idle take is seeded from the last frame of the speaking take, which locks the same dog, room, lighting and framing — not merely a similar-looking room. Idle clips are generated once per character and reused in every future episode, so they are capex rather than per-episode cost.
+ The idle take is seeded from the last frame of the speaking take, which locks the same dog, room, lighting and framing — not merely a similar-looking room. Without it the listeners stare blankly; with it they blink, tilt, scratch and yawn, and the grid reads as a real call.
@@ -108,7 +106,7 @@
01The photo
Breed, coat colour and markings are described in words. Naming the breed explicitly carries the likeness further than image resolution does.
02The topic
A real discussion — a thread, a podcast clip, an argument. The claim being made is preserved; only the stakes change.
03Director notes
The owner supplies the attitude. Loud and self-important, or flat and unimpressed. This is what makes it sound like their pet.
- 04The render
Each character is generated alone, twice — speaking and idle — then the four are composited into one grid with captions and branding.
+ 04The render
Each character is generated alone, twice — speaking and idle — then composited into one grid with captions and branding.
@@ -116,26 +114,31 @@
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 over who speaks when.
- - Seed continuity from the last frame. Growing the idle take out of the speaking take’s final frame guarantees an exact match. A shared background reference cannot do that, because it does not lock the animal.
- - Every line is verified, not assumed. Generated audio is transcribed back with Whisper and checked against the script before a clip is accepted. This caught a take where one character had absorbed another’s line.
- - Each shot gets a clean context. Generating several clips in one conversation caused dialogue to bleed between characters.
- - 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.
+ - 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 distinct dogs and exact control over who speaks when.
+ - Names belong in captions, not dialogue. The model refuses to speak real people’s names outright. Drawing them into the caption layer is reliable, unrestricted, and free to change — and puts more of the joke on screen than the spoken version managed.
+ - Seed continuity from the last frame. Growing the idle take out of the speaking take’s final frame guarantees an exact match. A shared background reference cannot, because it does not lock the animal.
+ - Every line is transcribed back and checked. This caught a take where one character had absorbed another’s line, and two takes where a list of names came out as mush.
+ - Do not write stage directions the model can read aloud. Dashes added to force pauses were spoken as filler words. Punctuation is not direction.
+ - Remux before publishing. 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.
What it costs
-
+
| Model | veo-3.1-lite, 720p, native audio |
|---|
- | Speaking clip | $0.40 per 8s |
|---|
- | Idle B-roll | $0.40 per 8s — once per character, then reused |
|---|
- | A four-dog short | $1.60 recurring, after a one-off $1.60 idle library |
|---|
- | Generation time | 41–62 seconds per clip |
|---|
+ | Any 8s clip | $0.40 |
|---|
+ | Generation time | 41–62 seconds |
|---|
+ | This 48s short, from nothing | $4.00 — ten clips |
|---|
+ | Each additional episode | $1.60 — four new lines; intro, cast and idles are reused |
|---|
+
+ Still rough
+ Honest state of play. Coined words give the model trouble — “okayest” lands somewhere between okayest and okay-us. Dense lists of proper nouns need splitting across takes rather than crammed into eight seconds. And every clip is a fresh roll of the dice: coat colour drifted tan-heavy on one early take and had to be regenerated.
+
+