Skip to content

armgit / hypit

Public Imported from GitHub
0

Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.

fix(reconstruction): always estimate take durations; close the anchoring gate

rpone7250710c3287
diff --git a/.agents/skills/hypit/references/playbooks/craft/sfx.md b/.agents/skills/hypit/references/playbooks/craft/sfx.md
index 327859f1..7eebaf68 100644
--- a/.agents/skills/hypit/references/playbooks/craft/sfx.md
+++ b/.agents/skills/hypit/references/playbooks/craft/sfx.md
@@ -31,7 +31,10 @@ Declare the source, normalize it to audio-only `SynchronizedMedia`, and place it
```
- Use `during={story.selection.NAME}` for a range, a Script Moment plus `for` for a point event, or
- explicit `start`/`end` timing in the SemanticTrack frame domain.
+ explicit `start`/`end` timing in the SemanticTrack frame domain — the last only for a program
+ with no speech to anchor to, the same gate `overlays.md` and `screen-demo.md` put on absolute
+ placement. Copying the reference's own seconds into an `start=`/`end=` is the same defect
+ `continuity.md` names for covering content.
- Use `playback="once"` for a discrete effect, loop only for a genuinely repeating texture, and
bounded pitch-preserving stretch only when the occupancy must fill an authored range.
- Use explicit trim, gain, fade-in, and fade-out. The Audio Track preserves source level and does not
diff --git a/.agents/skills/hypit/references/reconstruction/final-sources.md b/.agents/skills/hypit/references/reconstruction/final-sources.md
index f30665f1..4cafab10 100644
--- a/.agents/skills/hypit/references/reconstruction/final-sources.md
+++ b/.agents/skills/hypit/references/reconstruction/final-sources.md
@@ -27,20 +27,23 @@ consecutive Segments carrying one unbroken voiceover are one Segment with Select
`../playbooks/craft/generated-dependencies.md` says why — a Segment is a generation boundary, and
splitting a stretch the reference delivers unbroken invents a seam it does not have.
-## A take's duration is measured, not estimated
+## A take's duration is estimated, not read off the reference
-`estimate:Speech` predicts how long a line will take to say. In this route that prediction is the
-wrong input, because the reference already contains the answer: `prepare_reference` measured every
-word of it, so each Segment's real duration is the span from its first word's start to its last
-word's end in `transcript_ref`. Write that number on the take.
+Every take is generated, and the generated speech plays at its own pace, not the reference's. So
+each take's duration comes from `estimate:Speech` — the prediction of how long the generated line
+will be. Write that estimate on the take.
-An estimate is not close enough to skip this. A reconstruction whose Segments are each estimated a
-second long finishes several seconds longer than the reference, and every reveal, cut and overlay
-lands late against a program that no longer matches the thing it reconstructs. The estimate is for
-original authoring, where nobody has said the words yet.
+The reference's measured word timings describe how the original speaker delivered the line; the
+reconstruction re-speaks it, and the generated take will not match that recording second for
+second. Reading the reference's span onto the take fixes a length that has nothing to do with how
+the generator speaks.
-Keep the estimate only where the reference cannot answer: a line the reconstruction adds, or a
-Segment whose speech the reference never contains.
+Nothing depends on the estimate being exact. Script Selections bind every placed element to the
+words, and the SemanticTrack places the words where the generated audio actually has them, so a
+take that comes back a little long or short moves the words, not the bindings. This is also what
+lets a reconstruction survive the author changing the lines: the estimate recomputes from the new
+words, where a literal read off the old reference would not. `estimate:Speech` takes
+`story.segment.NAME.speech`, so the duration follows the script it is asked to predict.
Then check and wire, in that order. `../authoring.md` holds the check set — all four commands, not
only the Author Source — and `../preview.md` holds the graph check that comes after it. A Source that
diff --git a/.agents/skills/hypit/references/reconstruction/observers.md b/.agents/skills/hypit/references/reconstruction/observers.md
index 53f4cf33..19c42891 100644
--- a/.agents/skills/hypit/references/reconstruction/observers.md
+++ b/.agents/skills/hypit/references/reconstruction/observers.md
@@ -111,8 +111,8 @@ and do not put the gap to the author.
- **The transcript says when.** WhisperX measures every word locally on both paths, so the words and
their timings are exact whichever observer reads the pictures. That settles whether anyone is
- speaking at a given moment, and `final-sources.md` still takes Segment durations from
- `transcript_ref` as it always does.
+ speaking at a given moment, and where a word sits. It does not set a take's duration: the take is
+ generated and its length comes from `estimate:Speech`, as `final-sources.md` requires.
- **The pictures say who.** Attribute speech to the person the frames show speaking during the words
the transcript places there. A task that needs sound says so in its own prompt and asks for exactly
this reading.
diff --git a/.agents/skills/hypit/references/reconstruction/workflow.md b/.agents/skills/hypit/references/reconstruction/workflow.md
index 82338b72..0ad8272e 100644
--- a/.agents/skills/hypit/references/reconstruction/workflow.md
+++ b/.agents/skills/hypit/references/reconstruction/workflow.md
@@ -60,8 +60,9 @@ word, measured locally by WhisperX. It is not an observation: no model wrote it,
reaches an observer, and it does not go in the observation cache. It is identical on both observers,
and on the `agent` observer it is the only exact record of the sound. Read it whenever a decision depends on
when a word is said — placing each on-screen text reveal against the line that triggers it, timing a
-caption, checking that a voice observation matches what was actually spoken, or setting how long a
-take runs, which `final-sources.md` measures from these words rather than estimating. Do not run WhisperX
+caption, checking that a voice observation matches what was actually spoken, or judging a Segment's
+natural boundary. It does not set a take's duration: the take is generated and its length comes from
+`estimate:Speech`, as `final-sources.md` requires. Do not run WhisperX
by hand and do not ask a model to transcribe: the transcript is already there.
`transcript` reports `status`, `transcript_ref` and `word_count`. Read the words from