audio-router
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseDaymade audio router
Daymade 音频路由器
Choose a bundled specialist by the requested result. Locate this loaded
in the active catalog or invocation, follow symlinks
to its canonical path, and verify its parent is . Its parent's
parent is the audio suite root. Resolve the selected relative path against
the router directory and verify it is a direct sibling under that
root. Do not anchor resolution to the task's working directory or a remembered
cache path. may exist in Claude Code but is absent in
Codex; stop if the active Router path is ambiguous.
audio-router/SKILL.mdaudio-routerSKILL.md${CLAUDE_PLUGIN_ROOT}Read the selected child in full before acting. Continue a
truncated read and load that child's task-required references. The children
and their scripts remain installed; only their automatic catalog entries are
hidden. Claude users can still invoke their original
commands manually.
SKILL.md/daymade-audio:<child>| Requested result | Read this exact file |
|---|---|
Transcribe with StepFun | |
| Synthesize Chinese/Japanese speech or voiceover with StepFun, including prosody, emotions, or a compatible cloned voice | |
| Turn an existing meeting transcript or 妙记 text into 会议纪要; merge multiple minute drafts, review existing minutes against the transcript, or reconcile speaker labels from verified evidence | |
Do not select StepFun merely because a user says “transcribe this audio.”
General audio/video transcription, speaker diarization, audio preprocessing,
and subtitles retain the direct entry. Correcting
recognition mistakes in existing text retains the direct
entry. If the user has a raw meeting recording and needs it filed into its
project, use when installed; this table begins after a
transcript exists. Company-specific voice profiles may have their own TTS
owner; do not substitute StepFun solely from the word “voiceover.”
asr-transcribe-to-texttranscript-fixermeeting-ingestIf a task spans stages, read the owner of each stage before acting. Selecting
a StepFun child does not authorize a paid call or uploading audio. A request
for meeting minutes does not authorize guessing an anonymous speaker's real
identity; use only the evidence the child and project permit.
根据请求的结果选择一个内置专用 Skill。在当前生效的 Skill 目录或调用入口中定位这个已加载的 ,沿符号链接找到其规范路径,并验证其父目录为 。该父目录的父目录是音频套件根目录。以路由器目录为基准解析所选的相对路径,并确认它是该根目录的直接子级 。不要以任务的工作目录或记忆中的缓存路径作为解析基准。 在 Claude Code 中可能存在,但在 Codex 中不存在;如果当前生效的 Router 路径不明确,则停止操作。
audio-router/SKILL.mdaudio-routerSKILL.md${CLAUDE_PLUGIN_ROOT}执行操作前,完整读取所选子 Skill 的 。如果读取内容被截断,应继续读取,并加载该子 Skill 的任务所需参考资料。各子 Skill 及其脚本仍保持已安装状态,只有它们在自动目录中的条目被隐藏。Claude 用户仍可手动调用原有的 命令。
SKILL.md/daymade-audio:<child>| 请求的结果 | 读取此确切文件 |
|---|---|
使用 StepFun | |
| 使用 StepFun 合成中文/日文语音或配音,包括韵律、情绪或兼容的克隆声音 | |
| 将现有会议转录文本或妙记文本转换为会议纪要;合并多个会议纪要草稿;对照转录文本审查现有会议纪要;或根据经验证的证据校正说话人标签 | |
不要仅因为用户说“转录这段音频”就选择 StepFun。通用音视频转录、说话人分离、音频预处理和字幕处理仍使用直接的 入口。修正现有文本中的识别错误仍使用直接的 入口。如果用户有原始会议录音且需要将其归档到项目中,请在已安装 时使用该 Skill;本表从转录文本生成之后开始适用。公司专用的声音配置可能有其专属的 TTS 负责方;不要仅因为出现“voiceover”一词就改用 StepFun。
asr-transcribe-to-texttranscript-fixermeeting-ingest如果任务跨越多个阶段,请在执行前读取每个阶段对应的负责 Skill。选择 StepFun 子 Skill 并不代表获准发起付费调用或上传音频。请求生成会议纪要并不代表可以猜测匿名说话者的真实身份;只能使用该子 Skill 和项目允许的证据。