Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/audio-mixWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zju-real/easel/audio-mix)<a href="https://agentmods.dev/skills/zju-real/easel/audio-mix"><img src="https://agentmods.dev/badge/skills/zju-real/easel/audio-mix/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zju-real/easel/audio-mix"><img src="https://agentmods.dev/badge/skills/zju-real/easel/audio-mix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00182 | $0.01056 |
| Opus 5 | $0.00091 | $0.00528 |
| Sonnet 5 | $0.00036 | $0.00211 |
| Haiku 4.5 | $0.00018 | $0.00106 |
Grade A, and why
audio-mix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
音频混合（旁白 + BGM + 音效）
把多条音频同时叠加混成一轨，核心能力是闪避（ducking）——旁白说话时自动压低 背景音乐，人声清晰、音乐不抢。全部走
skills/shared/scripts/audio_mix.py， 不要手拼 amix/sidechaincompress。
前后顺序拼接（一段接一段）见 audio-editing
concat；给视频配乐见 video-editingbgm； 降噪见 audio-denoise。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 旁白 | 否 | 口播/配音主轨（给了则输出时长跟它走，并触发闪避） |
| BGM | 否 | 背景音乐（自动循环补足到旁白长度） |
| 音效 | 否 | 一个或多个音效，可指定各自出现时间点 |
（三者至少给一个。最典型："旁白 + BGM"。）
输出（outputs/主题名/）
- 混音后的单轨音频（mp3/wav/m4a，按输出后缀）
- 报告：轨数、时长、是否闪避
执行步骤
脚本路径（相对项目根）：skills/shared/scripts/audio_mix.py（mix -h 看参数）。
# 旁白 + BGM（默认自动闪避，BGM 循环补足到旁白长度）
python skills/shared/scripts/audio_mix.py mix \
--voice narration.mp3 --bgm music.mp3 --bgm-volume 0.25 \
-o outputs/主题名/final.mp3
# 关闭闪避（纯叠加）
python skills/shared/scripts/audio_mix.py mix --voice v.mp3 --bgm m.mp3 --no-duck -o out.mp3
# 旁白 + 定时音效（第 3.5s 一个叮，第 8s 一个 whoosh）
python skills/shared/scripts/audio_mix.py mix --voice v.mp3 \
--sfx ding.wav --sfx-at 3.5 --sfx whoosh.wav --sfx-at 8 -o out.mp3
调参
- 人声被音乐盖住：调低
--bgm-volume（默认 0.25）或确认闪避已开（默认开）。 - 闪避太猛/音乐一顿一顿：
--no-duck后手动压低--bgm-volume。 - BGM 比旁白短：默认自动循环；不想循环用
--bgm-loop-off。 - 音效太响/太轻：
--sfx-volume（默认 0.9）。
规则
- 有旁白时输出时长 = 旁白长度，BGM 自动循环/裁切对齐并在末尾淡出。
- 旁白 + BGM 默认开启闪避（人声优先）；不需要时显式
--no-duck。 --sfx与--sfx-at数量一致（或不给 --sfx-at 全部默认 0s）。- 混音不做响度归一（保留相对音量）；需统一响度先用 audio-editing
normalize。 - 产物统一进
outputs/主题名/。
参考来源
闪避用 ffmpeg sidechaincompress（以人声为控制信号压缩 BGM），是播客/口播视频保证人声清晰的
标准做法；多轨叠加用 amix。把 sidechain 接线与循环对齐封装成确定性脚本。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 68 lines · 182 tokens per session scan A f4a017f4c6ca
audio-mix is a skill published in the GitHub repository ZJU-REAL/Easel (710 stars, last pushed today), licensed Apache-2.0. It adds 182 tokens to every session and 1,056 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ppt-generation
Generate PPTX presentations from slide plan + content.
chart-visualization
Generate charts: select type, extract data, render image.
jacky-motion2-0-srt
A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.
video-podcast-maker
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…
video-podcast-maker-lite
Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…
video-podcast-maker-nano
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…