菜单
Transcribe audio files (podcasts, MP3s, interviews) using OpenAI Whisper. Use when the user wants to transcribe a podcast, audio file, or MP3. Also use when asked to "listen to" a podcast or audio.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Describes PHP and Laravel guidelines provided by Spatie. These rules result in more maintainable, and readable code.
Manage email marketing with the Mailcoach CLI — email lists, subscribers, campaigns, transactional emails, templates, automations, tags, and segments.
Create, schedule, and manage social media posts via Typefully. ALWAYS use this skill when asked to draft, schedule, post, or check tweets, posts, threads, or social media content for Twitter/X, LinkedIn, Threads, Bluesky, or Mastodon.
Update Spatie package documentation on spatie.be by re-importing docs for a given repo. Use after merging a PR that touches docs/, or when the user says 'update docs for [package]', 'rebuild docs for [repo]', 'import docs for [repo]', or invokes /update-spatie-docs [repo-name]. Takes a repo name argument (e.g., 'backup', 'laravel-medialibrary', 'laravel-pdf').
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative testing,' or 'ad performance optimization.' This skill covers generating ad creative at scale, iterating based on performance data, and enforcing platform character limits. For campaign strategy and targeting, see paid-ads. For landing page copy, see copywriting.
When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers. Also use when the user mentions 'AI SEO,' 'AEO,' 'GEO,' 'LLMO,' 'answer engine optimization,' 'generative engine optimization,' 'LLM optimization,' 'AI Overviews,' 'optimize for ChatGPT,' 'optimize for Perplexity,' 'AI citations,' 'AI visibility,' or 'zero-click search.' This skill covers content optimization for AI answer engines, monitoring AI visibility, and getting cited as a source. For traditional technical and on-page SEO audits, see seo-audit. For structured data implementation, see schema-markup.
| name | transcribe |
| description | Transcribe audio files (podcasts, MP3s, interviews) using OpenAI Whisper. Use when the user wants to transcribe a podcast, audio file, or MP3. Also use when asked to "listen to" a podcast or audio. |
| license | MIT |
| metadata | {"author":"spatie","version":"0.0.1"} |
Transcribe audio files using OpenAI Whisper (installed via Homebrew).
whisper CLI must be installed: brew install openai-whisperIf given a URL, download it:
curl -L -o /tmp/audio-file.mp3 "URL_HERE"
If given a podcast name/episode, search for the RSS feed or episode page to find the MP3 URL. Podcast hosting platforms like Transistor, Buzzsprout, Libsyn typically have direct MP3 URLs in their episode pages.
whisper /tmp/audio-file.mp3 --model small --language en --output_dir /tmp/whisper-output --output_format txt
Available models (speed vs accuracy tradeoff):
tiny - fastest, least accuratebase - fast, decent accuracysmall - good balance (recommended default)medium - slower, better accuracylarge - slowest, best accuracyFor non-English audio, omit the --language flag or specify the correct language code.
The transcript will be at /tmp/whisper-output/audio-file.txt
small model to keep it reasonablemedium or large--output_format srt