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 cyuanxv/ai-mandrama-skills --skill edge-tts-chinese-roleplaygit clone --depth 1 https://github.com/cyuanxv/ai-mandrama-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/cyuanxv/ai-mandrama-skills/edge-tts-chinese-roleplay)<a href="https://agentmods.dev/skills/cyuanxv/ai-mandrama-skills/edge-tts-chinese-roleplay"><img src="https://agentmods.dev/badge/skills/cyuanxv/ai-mandrama-skills/edge-tts-chinese-roleplay/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/cyuanxv/ai-mandrama-skills/edge-tts-chinese-roleplay"><img src="https://agentmods.dev/badge/skills/cyuanxv/ai-mandrama-skills/edge-tts-chinese-roleplay.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 | $0.00937 | $0.04161 |
| Opus 5 | $0.00468 | $0.02080 |
| Sonnet 5 | $0.00187 | $0.00832 |
| Haiku 4.5 | $0.00094 | $0.00416 |
Grade A, and why
edge-tts-chinese-roleplay 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
edge-tts 中文角色化 TTS 配音
何时使用本 Skill
- 任何中文内容需要"多角色 TTS 配音"且预算为 0(免费)
- 短剧/动态漫/有声小说/教程/Vlog/抖音解说/课程旁白
- 已踩过 macOS
say90% 中文 voice 是空音的坑 - 需要给视频按字幕时间码插入多段配音
- 念稿 TTS 没情绪起伏,要 SSML 调 rate/pitch
核心方法
第一步:装 edge-tts(一次性)
pip3 install edge-tts
edge-tts --list-voices | grep -E "zh-CN" | head -15
预期输出(实际可用的中文 voice):
zh-CN-XiaoxiaoNeuralFemale / News, Novel / Warmzh-CN-XiaoyiNeuralFemale / Cartoon, Novel / Livelyzh-CN-YunjianNeuralMale / Sports, Novel / Passionzh-CN-YunxiNeuralMale / Novel / Lively, Sunshinezh-CN-YunxiaNeuralMale / Cartoon, Novel / Cutezh-CN-YunyangNeuralMale / News / Professional, Reliable- 辽宁-XiaobeiNeural Female / Dialect / Humorous(东北话)
- 陕西-XiaoniNeural Female / Dialect / Bright(陕西话)
第二步:角色声线分配(4 类标配)
| 角色类型 | Voice | 风格描述 | 典型应用 |
|---|---|---|---|
| 爽文男主 / 阳光小说男 | zh-CN-YunxiNeural |
阳光男主,活泼,小说朗读型 | 陆明 / 韩立 / 男 vlog 主播 |
| 反派 / 粗暴男 / 怒吼路人 | zh-CN-YunjianNeural |
体育激情,粗暴男 | 队长1 / 路人惊恐喊救命 / 反派吼叫 |
| 萌系小丑 / 配角谄媚 | zh-CN-YunxiaNeural |
卡通可爱搞笑 | 配角男争抢 / 弹幕小丑 / 反差萌 |
| 系统女音 / 温柔旁白 | zh-CN-XiaoxiaoNeural |
温柔,新闻级,小说级 | 系统提示 / 旁白 / 智能助手 |
第三步:6 类情绪 rate/pitch 速查
edge-tts --voice "<voice>" --rate "<rate>" --pitch "<pitch>" \
--text "<台词>" --write-media output.mp3
| 情绪 | rate | pitch | 适用 | 示例 |
|---|---|---|---|---|
| 紧张惊恐喊叫 | +25% | +10Hz | 路人惊恐 / 反派怒吼 | "救命啊!" |
| 阳光调侃 | +8% | +3Hz | 男主轻松摆烂 | "不准训练哈!" |
| 沉重 OS 自嘲 | -5% | -3Hz | 男主内心独白 | "我叫陆明,上辈子内卷加班猝死" |
| 霸气定海一字 | -30% | -5Hz | 男主装逼定场 | "起——!" |
| 系统机械感 | -15% | -2Hz | 系统女音降速 | "恭喜宿主激活系统" |
| 谄媚小丑拔尖 | +20% | +10Hz | 配角谄媚抢戏 | "大佬选我!" |
第四步:ffmpeg 合到视频音轨
核心命令(多段 mp3 按时间码 adelay + volume 补 + amix 混合):
ffmpeg -y -i input_video.mp4 \
-i seg_01.mp3 -i seg_02.mp3 ... -i seg_15.mp3 \
-i bgm.wav \
-filter_complex "
[1:a]aresample=44100,adelay=500|500,volume=14[t1];
[2:a]aresample=44100,adelay=5500|5500,volume=14[t2];
...
[15:a]aresample=44100,adelay=52500|52500,volume=14[t15];
[16:a]aresample=44100,adelay=4000|4000,volume=0.18[bgm];
[t1][t2]...[t15][bgm]amix=inputs=16:dropout_transition=0[aout]" \
-map 0:v -map "[aout]" \
-c:v copy -c:a aac -b:a 192k -shortest \
output.mp4
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 · 214 lines · 937 tokens per session scan A 40722b9c4e14
edge-tts-chinese-roleplay is a skill published in the GitHub repository cyuanxv/ai-mandrama-skills (23 stars, last pushed 3mo ago), licensed MIT. It adds 937 tokens to every session and 4,161 once invoked, about $0.0047 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
story-to-video-studio
Turn a story, novel excerpt, treatment, or screenplay into a complete AI-video production and editable post-production package. Use when Codex needs to adapt narrative, design characters and locations, write a timed shooting script, generate storyboard and image-to-video prompts, manage generation budgets and approval…
frontend-design
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.
stage-plan
The "ingest + plan" half of end-to-end video orchestration — ingest the user's material from evidence, then decompose intent into ONE cross-modal EDL (plan.json: edit/generate/compose/provided segments + narration/music/caption tracks + a delivery promise), validate it with ovs plan validate. Trigger when the…
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.
stage-consistency
Multi-shot narrative & character consistency — a character bible with a locked front-portrait anchor, view-matched reference selection, recent-frame carry-forward, Cameo (a user photo as the lead), and global planning for long scripts/novels. Trigger on top of the generation line when the SAME character must look the…