all publishers

eatmoreduck

@eatmoreduck source repo

6 published skills

  1. ▌
    Yaya Asr · eatmoreduck bundle
    Transcribes any audio or video file into speaker-labeled text entirely on the local machine — no cloud, no login, no API key. Outputs plain text, SRT subtitles, an A/B dialogue transcript, and structured JSON. Use when the user shares a recording (meeting, interview, podcast, lecture, voice memo) and wants a transcript, subtitles, or "谁说了什么"; or says "转写", "语音转文字", "会议纪要", "录音转文字", "做字幕", "who said what". Apple Silicon required for the fast MLX path.
    0 installs
  2. ▌
    Yaya Xdl · eatmoreduck bundle
    Downloads X (Twitter) Space audio to a local m4a file — archive-first downloader. Use when the user shares an x.com/i/spaces link and asks to "下载 Space", "存个 Space", "归档 Space", "把录音存下来", or wants just the audio without transcription; also serves as the download step of yaya-xspace.
    0 installs
  3. ▌
    Yaya Corpus · eatmoreduck bundle
    文字稿进 → 可上架的中英双语音频出。 校对、清洗、分段、离线合成、双语字幕、标签内嵌,一条流水线走完。合成全程本地跑,稿子不出你的机器;免费、零登录、不需要任何云端账号。
    0 installs
  4. ▌
    Yaya Xspace · eatmoreduck bundle
    Turns an X (Twitter) Space into a distilled Chinese notes file — orchestrates yaya-xdl (download) and yaya-asr (transcribe with speaker labels), then distills while keeping every quote, keyword and enumeration intact. Use when the user shares an x.com/i/spaces link or Space audio and asks to "转写 Space", "Space 蒸馏", "把这场 Space 总结成干货", or wants who-said-what notes from a Space.
    0 installs
  5. ▌
    Yaya Diarize · eatmoreduck bundle
    Separates speakers in any audio entirely locally — outputs a who-spoke-when timeline (sherpa-onnx voiceprint clustering, no cloud, no transcript needed). Use when the user asks for "人声分离", "说话人分离", "谁在什么时候说话", "分轨", or wants speaker turns from an audio; also serves as the separation stage called by yaya-asr.
    0 installs
  6. ▌
    Boss Zhipin Scraper · eatmoreduck bundle
    Scrape BOSS直聘 (job listing site) via Chrome CDP. Searches jobs by keyword/city/filters, fetches JD details, outputs structured JSON/CSV with plaintext salary, and can summarize scraped results into a job-market prompt. Use when user wants to search/analyze jobs on BOSS直聘 or zhipin.com.
    4 installs