chore(home): re-enrich firstact voiceIds with gemini model

Browse Source

Re-ran scripts/enrich-firstacts-stepfun.mjs with gemini-3.1-flash-lite-preview
as the TEXT model (was deepseek-v4-flash). The new picks better match the
mysterious / cool / melancholic archetypes common in the curated cards
(e.g. 夜煌 清冷空灵+悲怆决绝 → lengyanyujie 冷艳御姐, was youyanvsheng).

Only stepfunVoiceId values changed across 52 cards; voice (Xiaomi) /
imageUrl / scene untouched. 0 failures across the 147-character run.

run: pnpm enrich:firstacts [--force] [--portrait]

...

This commit is contained in:

yuanzonghao

2026-06-15 14:03:34 +08:00

parent 17341cbd4a

commit 0166c5e0a9

52 changed files with 52 additions and 52 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

public/home/firstact-portrait/m1.json

+1 -1

File diff suppressed because one or more lines are too long