ワンクリックでManusで任意のスキルを実行

transcript-to-pdf

スター0

フォーク1

更新日2026年4月27日 20:16

Render a single transcript to a PDF using Typst, with the source file's modification timestamp and page numbers in the footer. Use when the user asks to "make a PDF of this transcript", "render to PDF", "transcript as PDF", or otherwise wants a printable single-version document. For multi-version (raw + cleaned + structured + blog) bundles, use `combine-versions` instead.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

danielrosehill

danielrosehill/Claude-Transcription-Plugin

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Transcript → PDF

Take one transcript file and render a clean PDF via Typst. Footer carries the original transcript timestamp on the left and page numbers on the right.

Inputs

Transcript path (markdown or plain text). Required.
Title (optional) — defaults to the filename stem.
Timestamp (optional) — defaults to the transcript file's mtime formatted as YYYY-MM-DD HH:MM.

Output

<stem>.pdf written next to the input file (or to --out if the user supplies one).

Typst template

Write a temporary .typ file with:

#set document(title: "<title>")
#set page(
  paper: "a4",
  margin: (x: 2cm, y: 2.2cm),
  footer: context [
    #set text(size: 9pt, fill: gray)
    #grid(
      columns: (1fr, 1fr),
      align: (left, right),
      [<timestamp>],
      [Page #counter(page).display() of #counter(page).final().first()],
    )
  ],
)
#set text(font: "IBM Plex Sans", size: 11pt)
#set par(justify: true, leading: 0.7em)

= <title>

<body — markdown converted to Typst>

Substitute <title>, <timestamp>, and <body> before compiling. Font: IBM Plex Sans if available, otherwise Typst default.

Markdown → Typst conversion (minimal)

Markdown	Typst
`# H1`	`= H1`
`## H2`	`== H2`
`bold`	`bold`
`italic`	`_italic_`
`code`	`code`
`- item`	`- item`
Blank line	Blank line (paragraph break)

Plain prose passes through unchanged. For anything richer (tables, code blocks, links), do a per-element pass.

Render

typst compile <stem>.typ <stem>.pdf

Delete the intermediate .typ after a successful compile unless the user asks to keep it.

Edge cases

No typst binary: instruct the user to install via cargo install --locked typst-cli or their distro's package manager. Do not silently fall back to a different format.
Very long transcripts (50+ pages): Typst handles this fine; just confirm with the user before rendering anything over ~200 pages so they can opt into a smaller font / tighter leading.
Diarized transcript (speaker-prefixed lines like Speaker 1: ...): preserve as-is; the bold/italic conversion already handles the **Speaker 1:** form many transcribers emit.

このリポジトリの他の Skills

同じリポジトリ

export-transcript

danielrosehill/Claude-Transcription-Plugin

Export a transcript (or any pipeline output) by emailing it, uploading to Google Drive, or copying to clipboard. Use when the user asks to send, email, upload, save to Drive, or copy a transcript.

2026-05-070

transcribe-podcast

danielrosehill/Claude-Transcription-Plugin

Transcribe a podcast episode and produce two outputs in one pass — (1) the raw API transcript exactly as the provider returned it, and (2) a podcast-formatted reading version with filler words removed, section headers added, and speaker labels preserved. Use whenever the user provides a podcast audio file or says "transcribe this podcast".

2026-04-280

messy-audio-fix

danielrosehill/Claude-Transcription-Plugin

Diagnose-and-treat workflow for very messy recordings where the standard preprocessor isn't enough. Generates a spectrogram, identifies problematic frequency bands (AC hum, rumble, narrow-band whines, broadband hiss, clipping), and proposes targeted ffmpeg filters. ONLY use when the user explicitly invokes it — the normal pipeline runs `preprocess-for-transcription` directly and skips diagnostic work. Trigger phrases the user might use — "this audio is messy", "transcription failed because of noise", "fix this rough recording", "the audio is bad and the transcript is garbage".

2026-04-280

denoise

danielrosehill/Claude-Transcription-Plugin

Remove background noise from an audio file. Cloud providers (Auphonic default, ElevenLabs, Dolby.io) or local (DeepFilterNet ML, ffmpeg afftdn non-ML). Use when the user asks to denoise, clean up noise, remove hum/hiss, or enhance speech audio before transcription.

2026-04-280

preprocess-for-transcription

danielrosehill/Claude-Transcription-Plugin

Prepare audio for transcription — format normalise (mono/16kHz/opus), loudness normalise (EBU R128), and collapse long silences (silero-vad). Optional denoise pass. Use before sending to AssemblyAI or any ASR for cleaner results, smaller uploads, and lower cost. Use when the user asks to "preprocess audio", "prep for transcription", "clean up a recording before sending it", or just hands over a raw voice memo to be transcribed.

2026-04-280

transform-style

danielrosehill/Claude-Transcription-Plugin

Apply a stylistic / formatting transformation to a transcript using a named prompt from the user's Text-Transformation-Prompt-Library (206 transformations covering blog outlines, briefs, business correspondence, analysis documents, meeting notes, and more). Use when the user asks to "convert this to <style>", "format like a <type>", or names a specific transformation. Fetches the catalog on demand and caches it; never commits the prompts into this plugin.

2026-04-280

name	transcript-to-pdf
description	Render a single transcript to a PDF using Typst, with the source file's modification timestamp and page numbers in the footer. Use when the user asks to "make a PDF of this transcript", "render to PDF", "transcript as PDF", or otherwise wants a printable single-version document. For multi-version (raw + cleaned + structured + blog) bundles, use `combine-versions` instead.

Transcript → PDF

Take one transcript file and render a clean PDF via Typst. Footer carries the original transcript timestamp on the left and page numbers on the right.

Inputs

Transcript path (markdown or plain text). Required.
Title (optional) — defaults to the filename stem.
Timestamp (optional) — defaults to the transcript file's mtime formatted as YYYY-MM-DD HH:MM.

Output

<stem>.pdf written next to the input file (or to --out if the user supplies one).

Typst template

Write a temporary .typ file with:

#set document(title: "<title>")
#set page(
  paper: "a4",
  margin: (x: 2cm, y: 2.2cm),
  footer: context [
    #set text(size: 9pt, fill: gray)
    #grid(
      columns: (1fr, 1fr),
      align: (left, right),
      [<timestamp>],
      [Page #counter(page).display() of #counter(page).final().first()],
    )
  ],
)
#set text(font: "IBM Plex Sans", size: 11pt)
#set par(justify: true, leading: 0.7em)

= <title>

<body — markdown converted to Typst>

Substitute <title>, <timestamp>, and <body> before compiling. Font: IBM Plex Sans if available, otherwise Typst default.

Markdown → Typst conversion (minimal)

Markdown	Typst
`# H1`	`= H1`
`## H2`	`== H2`
`bold`	`bold`
`italic`	`_italic_`
`code`	`code`
`- item`	`- item`
Blank line	Blank line (paragraph break)

Plain prose passes through unchanged. For anything richer (tables, code blocks, links), do a per-element pass.

Render

typst compile <stem>.typ <stem>.pdf

Delete the intermediate .typ after a successful compile unless the user asks to keep it.

Edge cases

No typst binary: instruct the user to install via cargo install --locked typst-cli or their distro's package manager. Do not silently fall back to a different format.
Very long transcripts (50+ pages): Typst handles this fine; just confirm with the user before rendering anything over ~200 pages so they can opt into a smaller font / tighter leading.
Diarized transcript (speaker-prefixed lines like Speaker 1: ...): preserve as-is; the bold/italic conversion already handles the **Speaker 1:** form many transcribers emit.