kangwan/20260512-skg-tk
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

auto-save 2026-05-18 14:30 (~5)

Browse Source
This commit is contained in:
kang
2026-05-18 14:30:08 +08:00
parent b5b1e43624
commit e6a5ea46a6
5 changed files with 26 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
RULES.md
View File

@@ -56,7 +56,8 @@
- `ASR_TIMEOUT_SECONDS`：远端 ASR / 音频分析单次请求超时，默认 45 秒，避免第一步长时间停在转录中
- `LOCAL_ASR_BIN` / `LOCAL_ASR_MODEL` / `LOCAL_ASR_TIMEOUT_SECONDS`：本机 ASR 兜底，默认使用 `/opt/homebrew/bin/mlx_whisper` + `mlx-community/whisper-tiny`，用于当前 SKG 网关 `/audio/transcriptions` 不可用时生成真实逐句时间轴
- `TRANSLATE_MODEL`：字幕翻译模型，默认 `gemini-2.5-flash`
- `REWRITE_MODEL`：通用改写/分镜描述模型，默认 `gemini-2.5-pro`
- `REWRITE_MODEL`：通用改写/分镜描述模型，默认 `gpt-4o`
- `VISION_MODEL`：关键帧画面理解模型，默认 `gpt-4o`
- `AUDIO_REWRITE_MODEL`：后续音频口播改写模型，默认跟随 `REWRITE_MODEL`；当前第一步不默认调用口播改写，只保留原文案和声音分析
- `AUDIO_PRODUCT_BRIEF`：音频口播改写时注入的 SKG 产品卖点
- `PRODUCT_VIEW_MODEL`：同一产品素材池的视角标注/自动识别模型；当前按项目要求强制使用 `gpt-image-2`