openai-whisper
Perform secure, local audio-to-text transcription using the Whisper command line tool.
Install
mkdir -p .claude/skills/openai-whisper && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/690" && unzip -o skill.zip -d .claude/skills/openai-whisper && rm skill.zipInstalls to .claude/skills/openai-whisper
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Local speech-to-text with the Whisper CLI (no API key).Key capabilities
- →Transcribe audio files to text
- →Generate SRT caption files
- →Translate audio content to English
- →Support multiple model sizes for speed or accuracy
How it works
The skill utilizes the Whisper CLI to process audio files locally on the machine, downloading necessary models to a cache directory on the first execution.
Inputs & outputs
When to use openai-whisper
- →Transcribing meeting recordings
- →Generating captions for video
- →Converting voice memos to notes
- →Processing audio logs
About this skill
Whisper (CLI)
Use whisper to transcribe audio locally.
Quick start
whisper /path/audio.mp3 --model medium --output_format txt --output_dir .whisper /path/audio.m4a --task translate --output_format srt
Notes
- Models download to
~/.cache/whisperon first run. --modeldefaults toturboon this install.- Use smaller models for speed, larger for accuracy.
When not to use it
- →When an internet-connected cloud transcription service is required
- →When the system lacks sufficient local storage for model caching
Prerequisites
Limitations
- →Models are downloaded to ~/.cache/whisper
- →Performance depends on local hardware capabilities
How it compares
This approach performs transcription entirely offline without requiring API keys or external cloud processing.
Compared to similar skills
openai-whisper side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| openai-whisper (this skill) | 38 | 2mo | No flags | Beginner |
| whisper-transcription | 1 | 2mo | Review | Intermediate |
| xhs-note-creator | 4 | 4mo | Review | Beginner |
| google-docs-skill | 0 | 2mo | Caution | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by openclaw
View all by openclaw →You might also like
whisper-transcription
benchflow-ai
Transcribe audio/video to text with word-level timestamps using OpenAI Whisper. Use when you need speech-to-text with accurate timing information for each word.
xhs-note-creator
comeonzhj
小红书笔记素材创作技能。当用户需要创建小红书笔记素材时使用这个技能。技能包含：根据用户的需求和提供的资料，撰写小红书笔记内容（标题+正文），生成图片卡片（封面+正文卡片），以及发布小红书笔记。
google-docs-skill
javimosch
Direct access to the Google Docs API using OAuth 2.0. Create documents, insert and format text, and manage document content.
rfp_contents
yellowCornSalad
공고 카드의 콘텐츠 품질 점검 + LLM 자동 요약. 예산·기간 정확성, 본문 가독성, 키워드 매칭 정확성, 상세보기 가독성 5축 점검 + 카드에 본문+첨부 종합 150자 요약을 ai_summary 컬럼에 저장.
video-downloader
ComposioHQ
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
anthropics
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.