Audio Ducking
sonilo-ai/skills
Duck a music bed under a voice track using Sonilo — automatically lowers the music wherever the voice speaks and lifts it back in the gaps.
为旁白/解说剧本逐分镜生成旁白配音（TTS）。当 TTS 项目首轮自动剪辑需要补齐缺失配音、用户要求生成或重新生成某个分镜或某集旁白配音，或批量配音中断需要补齐时使用。
Install Generate Narration Audio
$ npx skills add ArcReel/ArcReel --skill generate-narration-audio -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ArcReel/ArcReel generate-narration-audio --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ArcReel/ArcReel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent_runtime_profile/.claude/skills/generate-narration-audio .claude/skills/generate-narration-audio && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "generate-narration-audio" agent skill from https://github.com/ArcReel/ArcReel/tree/main/agent_runtime_profile/.claude/skills/generate-narration-audio into .claude/skills/generate-narration-audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-narration-audio", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ArcReel/ArcReel/tree/main/agent_runtime_profile/.claude/skills/generate-narration-audioType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ArcReel/ArcReel --skill generate-narration-audio -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ArcReel/ArcReel generate-narration-audio --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArcReel/ArcReel.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agent_runtime_profile/.claude/skills/generate-narration-audio .agents/skills/generate-narration-audio && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "generate-narration-audio" agent skill from https://github.com/ArcReel/ArcReel/tree/main/agent_runtime_profile/.claude/skills/generate-narration-audio into .agents/skills/generate-narration-audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-narration-audio", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ArcReel/ArcReel --skill generate-narration-audio -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ArcReel/ArcReel generate-narration-audio --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArcReel/ArcReel.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agent_runtime_profile/.claude/skills/generate-narration-audio .cursor/skills/generate-narration-audio && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "generate-narration-audio" agent skill from https://github.com/ArcReel/ArcReel/tree/main/agent_runtime_profile/.claude/skills/generate-narration-audio into .cursor/skills/generate-narration-audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-narration-audio", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ArcReel/ArcReel.git --path agent_runtime_profile/.claude/skills/generate-narration-audio--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ArcReel/ArcReel --skill generate-narration-audio -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ArcReel/ArcReel generate-narration-audio --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArcReel/ArcReel.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agent_runtime_profile/.claude/skills/generate-narration-audio .gemini/skills/generate-narration-audio && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "generate-narration-audio" agent skill from https://github.com/ArcReel/ArcReel/tree/main/agent_runtime_profile/.claude/skills/generate-narration-audio into .gemini/skills/generate-narration-audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-narration-audio", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ArcReel/ArcReel generate-narration-audioInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ArcReel/ArcReel --skill generate-narration-audio -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ArcReel/ArcReel.git skills-src && mkdir -p .github/skills && cp -r skills-src/agent_runtime_profile/.claude/skills/generate-narration-audio .github/skills/generate-narration-audio && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "generate-narration-audio" agent skill from https://github.com/ArcReel/ArcReel/tree/main/agent_runtime_profile/.claude/skills/generate-narration-audio into .github/skills/generate-narration-audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-narration-audio", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ArcReel/ArcReel --skill generate-narration-audio -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ArcReel/ArcReel generate-narration-audio --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArcReel/ArcReel.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agent_runtime_profile/.claude/skills/generate-narration-audio .opencode/skills/generate-narration-audio && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "generate-narration-audio" agent skill from https://github.com/ArcReel/ArcReel/tree/main/agent_runtime_profile/.claude/skills/generate-narration-audio into .opencode/skills/generate-narration-audio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "generate-narration-audio", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
generate-narration-audio- GitHub stars
- 5.4k
- Token cost
- ~524 tokens
- SKILL.md length
- 138 words
- Files
- 1
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
为旁白/解说剧本逐分镜生成旁白配音（TTS）。当 TTS 项目首轮自动剪辑需要补齐缺失配音、用户要求生成或重新生成某个分镜或某集旁白配音，或批量配音中断需要补齐时使用。
- Works in 3 steps: 状态检测 — 读取剧本，检查各分镜的… → 入队生成 — 调用 MCP 工具，任务经生成队列由 worker… → 汇报 — 汇总成功/失败明细展示给用户
- Tasks that involve Text to speech and voice
- SKILL.md covers 工具调用, 工作流程, 断点续传 and 错误处理
- Calls python
What it does
Generate Narration Audio is an agent skill from ArcReel/ArcReel. 为旁白/解说剧本逐分镜生成旁白配音（TTS）。当 TTS 项目首轮自动剪辑需要补齐缺失配音、用户要求生成或重新生成某个分镜或某集旁白配音，或批量配音中断需要补齐时使用。
Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative, covering Text to speech and voice. It works with Model Context Protocol. The repository describes itself as: AI Agent 驱动的开源可自部署视频工作台：将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿，支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video workspace for stories, storyboards and short-form video production. The licence is AGPL-3.0.
When your agent uses it
- Tasks that involve Text to speech and voice
Example prompts
- “/generate-narration-audio”
Requirements
- Python 3
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 状态检测 — 读取剧本，检查各分镜的 generated_assets.narration_audio，统计缺失分镜并告知用户
- 入队生成 — 调用 MCP 工具，任务经生成队列由 worker 处理，工具等待全部完成后返回逐分镜结果
- 汇报 — 汇总成功/失败明细展示给用户
What it can do on your machine
Read from SKILL.md and the folder at commit 08ab3b3. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Generate Narration Audio loads about 524 tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 138 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from ArcReel/ArcReel at commit 08ab3b3, republished under its AGPL-3.0 licence (© ArcReel). 138 words, ~524 tokens.
Download SKILL.mdSave it as
.claude/skills/generate-narration-audio/SKILL.md (or your agent's skills folder).- name
- generate-narration-audio
- description
- 为旁白/解说剧本逐分镜生成旁白配音（TTS）。当 TTS 项目首轮自动剪辑需要补齐缺失配音、用户要求生成或重新生成某个分镜或某集旁白配音，或批量配音中断需要补齐时使用。
生成旁白配音
为旁白/解说创作类型剧本的每个分镜，以该分镜的 novel_text 原文合成一段旁白配音，
写回该分镜的 generated_assets.narration_audio（输出 audio/segment_{segment_id}.wav）。
只依赖剧本，不依赖分镜图/视频——剧本生成后即可推进。
工具调用
重要：生成旁白配音必须调用下列 MCP 工具入队。此 skill 不提供任何 Python/Shell 脚本，不得用 BASH 调 python .../scripts/*.py。
通过 MCP 工具入队：
| 操作 | 工具 |
|---|---|
| 全集补齐（默认，所有缺旁白配音的分镜） | mcp__arcreel__generate_narration_audio({"script": "episode_1.json"}) |
| 指定批量范围 | mcp__arcreel__generate_narration_audio({"script": "episode_1.json", "segment_ids": ["E1S01", "E1S02"]}) |
| 单分镜重生 | mcp__arcreel__generate_narration_audio({"script": "episode_1.json", "segment_ids": ["E1S05"]}) |
选择规则：不传
segment_ids则只为缺narration_audio的分镜入队——已失效但仍可用的旧配音会被复用，不自动重生； 显式传入的分镜即使已有旁白配音也会重新合成（用于换音色/语速后重生）。调用时机：TTS 项目首轮自动剪辑时按缺失补齐，项目选择 TTS 即已授权，无需另行确认； 用户也可随时要求生成。stale 配音仅按用户要求重合成；后期配音项目无需 TTS。 视频生成不依赖旁白配音，两者互不等待。 新旁白配音完成后请用户试听确认。
依赖：generation worker 必须在线（audio 独立通道）；项目的旁白交付方式是「TTS 配音」。TTS 模型、音色与语速 都取自项目设置里的 TTS 快照，与全局默认无关。
改音色/语速：用户要求"这个项目旁白用 X 音色 / 语速 1.2"时，调
mcp__arcreel__patch_project({"settings": {"narration_voice": "X", "narration_speed": 1.2}})改项目的 TTS 快照（只影响当前项目；narration_speed传null表示不向供应商传语速）。改完后，按旧模型、音色或语速 生成的旁白配音读作 stale：仍可试听、参与剪辑，全集补齐不会重生它们；要换成新设置，点名这些分镜重新合成。
工作流程
- 状态检测 — 读取剧本，检查各分镜的
generated_assets.narration_audio，统计缺失分镜并告知用户 - 入队生成 — 调用 MCP 工具，任务经生成队列由 worker 处理，工具等待全部完成后返回逐分镜结果
- 汇报 — 汇总成功/失败明细展示给用户
断点续传
中断（服务重启、任务失败、会话断开）后重新调用不传 segment_ids 的全集补齐即可：
已有旁白配音的分镜自动跳过，只补缺失分镜，不重复扣费。
错误处理
- 单分镜失败不影响批次：工具返回
requested / succeeded / failed / blocked的逐 ID 结果 - 按
failed/blocked里每一项自带的问题码与下一步动作决定重试还是先改输入，不要读文本猜 - 可重试的分镜用
segment_ids精确重试 - 工具返回
narration_delivery_post_production时，告知用户这个项目的旁白由后期配音交付、视频不受影响； 用户主动想要 in-app 旁白时，请其在 Web 项目设置里把交付方式改为 TTS 配音后重试 - 工具返回
narration_tts_*项目配置问题时，同样说明后期配音这条路照常可用；继续做视频不需要 TTS。 只有用户主动想要 in-app 旁白时，才引导其到 Web 项目设置补齐 TTS 模型或音色后重试
© ArcReel, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in agent_runtime_profile/.claude/skills/generate-narration-audio of ArcReel/ArcReel.
Open the folder on GitHubat commit 08ab3b3
Compare with similar skills
Generate Narration Audio next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Generate Narration Audio this skillArcReel/ArcReel | 5.4k | — | ~524 | Automated safety check: Pass | AGPL-3.0 | |
| Audio Duckingsonilo-ai/skills | 115 | — | ~1.8k | Automated safety check: Notes | MIT | |
| Auto Dubbingsonilo-ai/skills | 115 | — | ~4.5k | Automated safety check: Notes | MIT | |
| Proofreadsonilo-ai/skills | 115 | — | ~4.4k | Automated safety check: Notes | MIT | |
| Voiceguaardvark/guaardvark | 257 | — | ~798 | Automated safety check: Pass | MIT | |
| Task Recoverysonilo-ai/skills | 115 | — | ~2.1k | Automated safety check: Notes | MIT |
Similar skills
Auto Dubbing
sonilo-ai/skills
Dub a video into one or more other languages using Sonilo, translating and re-voicing the speech into a new video per language.
Proofread
sonilo-ai/skills
Transcribe a video with Sonilo and translate the transcript into editable .srt files — one per target language, plus the detected source language — so the wording can be read and corrected before…
Voice
guaardvark/guaardvark
Narration and text-to-speech on the user's machine through Guaardvark's Audio Foundry (Chatterbox, Kokoro, Piper) and consent-gated voice cloning from a reference clip.
Task Recovery
sonilo-ai/skills
Recover the result of a timed-out Sonilo generation call using its taskid.
Scenario Audio
scenario-labs/skills
A skill your agent uses when generating or handling audio on Scenario via MCP.
More from ArcReel/ArcReel
All 18 skills in this repoPR AI Review Loop
ArcReel/ArcReel
PR AI review 收敛。用户或 team-lead 要求启动或继续审查—修复循环时使用；供本地实现者或受委派的 review-looper 调用，不用于 GitHub reviewer 产出审查意见或仅处理单条评论。
Tech Doc Style Chinese
ArcReel/ArcReel
在撰写、改写、校对或审阅中文技术文档、产品文案、界面文案、Markdown 文档、API 说明、操作手册、故障排查或运维文档时使用。采用克制、准确、可扫读的中文技术写作风格；保留原文事实、限制和机器可读内容；按任务读取术语排版、API 状态文案、项目覆盖或受控中文技术写作参考。
Translate Docs
ArcReel/ArcReel
Translate every dirty ArcReel documentation source into English and refresh the translation lockfile.
Adapt Custom Endpoint
ArcReel/ArcReel
当用户要求把采用 JSON 提交后轮询协议的视频或图片供应商接入 ArcReel，或要求编写、验证、测试、保存自定义调用端点定义时使用。
Afk Team Workflow
ArcReel/ArcReel
把一个 Spec 的全部子 issue（或一组显式 issue）组建团队无人值守跑到全部合并或明确暂停. An agent skill from ArcReel/ArcReel.
Update Docs
ArcReel/ArcReel
根据最近的 git 改动，更新面向用户的文档（README 双语、入门教程、部署、剪映导出等）。手动调用. An agent skill from ArcReel/ArcReel.
Related
Works with
Categories
Questions about Generate Narration Audio
What does Generate Narration Audio do?
为旁白/解说剧本逐分镜生成旁白配音（TTS）。当 TTS 项目首轮自动剪辑需要补齐缺失配音、用户要求生成或重新生成某个分镜或某集旁白配音，或批量配音中断需要补齐时使用。. Generate Narration Audio is an agent skill from ArcReel/ArcReel.
When should I use Generate Narration Audio?
Generate Narration Audio fits situations like: tasks that involve Text to speech and voice.
How do I install Generate Narration Audio in Claude Code?
Run `npx skills add ArcReel/ArcReel --skill generate-narration-audio -a claude-code`. Or copy the skill folder (agent_runtime_profile/.claude/skills/generate-narration-audio in ArcReel/ArcReel) into .claude/skills/generate-narration-audio in your project. Claude Code loads it when a task matches its description.
How do I install Generate Narration Audio in Codex?
Run `npx skills add ArcReel/ArcReel --skill generate-narration-audio -a codex`. Or copy the skill folder (agent_runtime_profile/.claude/skills/generate-narration-audio in ArcReel/ArcReel) into .agents/skills/generate-narration-audio in your project. Codex loads it when a task matches its description.
Can I use Generate Narration Audio in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ArcReel/ArcReel --skill generate-narration-audio -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/generate-narration-audio, .gemini/skills/generate-narration-audio, .github/skills/generate-narration-audio and .opencode/skills/generate-narration-audio in your project.
What does Generate Narration Audio need to run?
Going by SKILL.md and its folder, Generate Narration Audio needs the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Generate Narration Audio access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Generate Narration Audio safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Generate Narration Audio use?
Generate Narration Audio is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Generate Narration Audio use?
About 524 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Generate Narration Audio?
Skills that share tags, products or a category with Generate Narration Audio: Audio Ducking (sonilo-ai/skills, 115 stars), Auto Dubbing (sonilo-ai/skills, 115 stars), Proofread (sonilo-ai/skills, 115 stars) and Voice (guaardvark/guaardvark, 257 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Generate Narration Audio?
ArcReel (a GitHub organization) maintains it in ArcReel/ArcReel, which has 5,412 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on October 9, 2026.
Source: ArcReel/ArcReel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.