Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add chenyuxiaojin/video-agent-skills --skill video-agent-voicegit clone --depth 1 https://github.com/chenyuxiaojin/video-agent-skillsWrote 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/chenyuxiaojin/video-agent-skills/video-agent-voice)<a href="https://agentmods.dev/skills/chenyuxiaojin/video-agent-skills/video-agent-voice"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-voice/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/chenyuxiaojin/video-agent-skills/video-agent-voice"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-voice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00150 | $0.03208 |
| Opus 5 | $0.00075 | $0.01604 |
| Sonnet 5 | $0.00030 | $0.00642 |
| Haiku 4.5 | $0.00015 | $0.00321 |
Grade A, and why
video-agent-voice 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-agent-voice(配音师)
职责边界
- ✅ 将逐字稿转为语音文件
- ✅ 生成精确时间戳的字幕文件
- ✅ 根据分镜表的情绪标注调整语速和情感
- ✅ 为自录音模式生成配音指导表
- ❌ 修改逐字稿内容(编剧负责)
- ❌ 设计画面(分镜师负责)
输入 → 输出
- 输入:
script.md+storyboard.md(可选,用于情绪标注) - 输出:
audio/voiceover.mp3audio/subtitles.srtaudio/voice-direction.md(配音指导表)
引擎选择
| 引擎 | 成本 | 中文质量 | 情绪控制 | 适用场景 |
|---|---|---|---|---|
| MiniMax Speech-02 | 低 | 最高(全球#1) | emotion 参数 + 停顿标记 | 正式发布(中文首选) |
| Edge-TTS | 免费 | 中等 | SSML 语速/音调 | 快速测试、草稿 |
| ElevenLabs | 高 | 差(WER 16%) | Prompt 情感描述 | 英文视频 |
| 自录音 | 免费 | 最高 | 完全自控 | 追求最佳效果 |
- 默认使用 MiniMax Speech-02(中文质量全球第一,价格仅 ElevenLabs 的 1/4)
- 如果 project.json 中指定
tts_engine: edge,使用 Edge-TTS(免费草稿) - 如果指定
tts_engine: elevenlabs,使用 ElevenLabs API(仅适合英文) - 如果指定
tts_engine: manual,跳过语音生成,仅生成字幕模板和配音指导表
MiniMax 声音克隆(可选)
支持用 10 秒录音克隆自己的声音,克隆后可反复使用:
python scripts/minimax_tts.py clone <你的录音.mp3> --voice-id myvoice001
克隆语音 7 天不使用会被自动删除,需重新克隆。克隆价格:9.9 元/次。
执行步骤
步骤 1:提取纯文本
python scripts/extract_plain_text.py <project>/script.md <project>/script-plain.txt
过滤规则(从 script.md 中去除非朗读内容):
- 去除
> 场景提示:...行 - 去除
【出处:...】行 - 去除 Markdown 标题行(
## 案例一:...) - 去除元数据行(
> 逐字稿 | 目标时长:...) - 去除分隔线(
---) - 保留所有正文段落(这些是要朗读的内容)
步骤 2:生成情绪节奏映射
如果存在 storyboard.md,读取每个镜头的情绪/节奏标注,生成情绪映射:
python scripts/build_emotion_map.py <project>/storyboard.md <project>/script-plain.txt <project>/audio/emotion-map.json
输出 emotion-map.json:
[
{
"segment": 1,
"text": "你有没有想过一个问题:为什么你学了那么多时间管理方法...",
"mood": "焦虑、快切",
"pace": "fast",
"ssml_rate": "+15%",
"ssml_pitch": "+5%",
"elevenlabs_style": "urgent, slightly anxious",
"direction_note": "语速偏快,带一点焦虑感,像在追问观众"
},
{
"segment": 5,
"text": "Cal Newport 在《Deep Work》这本书里提出了一个概念...",
"mood": "权威、可信",
"pace": "normal",
"ssml_rate": "+0%",
"ssml_pitch": "-3%",
"elevenlabs_style": "calm, authoritative",
"direction_note": "语速正常,声音沉稳,引用专家时要有权威感"
},
{
"segment": 12,
"text": "一天 8 小时,真正能用来做深度工作的时间,可能连 2 小时都不到",
"mood": "震惊、冲击",
"pace": "slow_then_pause",
"ssml_rate": "-10%",
"ssml_pitch": "+0%",
"elevenlabs_style": "dramatic pause, emphasis on the number",
"direction_note": "说到'2 小时'之前稍微停顿,然后重音落在这个数字上,让观众感受冲击"
}
]
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 302 lines · 150 tokens per session scan A 29a778324fae
video-agent-voice is a skill published in the GitHub repository chenyuxiaojin/video-agent-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 150 tokens to every session and 3,208 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
suggest-sfx
The SFX pass. Analyze a short's beats + narration and propose tasteful sound effects synced to them, drawing from (and growing) a shared, reusable SFX library, then render an SFX-mixed audition preview. Use when the user wants to "add SFX / sound effects", "suggest sfx", "score the transitions", "sound-design this…
make-ai-short
Build a GENERATIVE-pixels vertical short (1080×1920, 35-40s) end-to-end — a recurring locked character animated by a fal video model (Seedance 1.5 Pro default) under a philosophical/story VO, composited in Remotion with word-synced captions, SFX audition, seamless frame-0==last-frame loop. Use when the user wants to…
make-short
Build a fully-synthetic vertical short (1080×1920, 40s) end-to-end from a topic — script + beats.json, linked TSX beats over a persistent canvas, phone-scale QA, render, ElevenLabs voice with exact word-synced captions, SFX audition, optional music bed. Use when the user wants to "make a short", "create a shorts…
make-vox
Build a Vox-style LAYERED-COLLAGE vertical short end-to-end — script + scene dissection into image layers, layer production (AI images via genimage.py + cutout.py, HTML→PNG, SVG-in-TSX), choreographed TSX assembly on the collage kit (CollageBoard camera, parallax, cutouts, chips, routes), frame QA, render, then…
talking-head-edit
Edit interviews, lessons, commentary, podcasts, and direct-to-camera recordings built around speech. Use it to remove dead air, filler words, false starts, repeated lines, and discarded retakes while preserving natural delivery and keeping captions aligned. When the user asks for visual enhancement, also use it for…
montage-edit
Discover the governing emotion and visual motifs in a body of footage, then compose a montage whose image, rhythm, sound, and text form one intentional experience.