vault-sync: 2026-10-16 00:01 (jimmy)

2026-10-16 00:01:34 -07:00
parent eb54b93880
commit 5083eca6ae
13 changed files with 1472 additions and 0 deletions
@@ -0,0 +1,15 @@
+---
+tags: [video-stack, lessons]
+updated: 2026-10-15
+---
+# Lessons Learned
+Back to [[Video Stack - Overview]]
+
+- A Kokoro-made reference makes Chatterbox clones flat with odd pauses. Use a real human reference (the user's recording worked well; leave more headroom, it peaked at -0.1 dBFS).
+- Generate one sentence at a time (best of several seeds, ~200 ms gaps) to avoid strange pauses.
+- Copywriting: short spoken sentences, numbers written as spoken words, ~105 words per 45 s, leave ~2 s spare. Number-heavy long lines made Prop 1 sound awkward.
+- Gemini reads directions aloud unless they go in the style field.
+- Music must add feel: civic_tension and piano B were rejected; option A (dark low strings, slow heartbeat pulse) chosen for Prop 1. If code-composed music misses twice, use a richer generator.
+- ElevenLabs free tier was blocked for TTS ("unusual activity"); not retried.
+- HyperFrames is easier for local models than Remotion (plain HTML per scene).
+- Pick an authoritative male voice for political ads.