菜单
OpenAI Whisper API: audio transcription, translation, structured output, large file handling
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
| name | openai-whisper-api |
| cluster | community |
| description | OpenAI Whisper API: audio transcription, translation, structured output, large file handling |
| tags | ["whisper","api","transcription","openai"] |
| dependencies | [] |
| composes | [] |
| similar_to | [] |
| authorization_required | false |
| scope | general |
| model_hint | claude-sonnet |
| embedding_hint | openai whisper api transcription audio translation |
| clawhub_install | clawhub install openai-whisper-api |
| note | NOT installed via ClaWHub CLI — registered in Neo4j skill graph only. To activate: clawhub install openai-whisper-api |
OpenAI Whisper API: audio transcription, translation, structured output, large file handling
clawhub install openai-whisper-api
This skill is registered in the Neo4j skill graph for discovery purposes only. It is NOT installed via the traditional ClaWHub methodology. When a task matches this skill, the agent will inform you to install it if needed.
Secrets/API key management via 1Password CLI (op). Vault items, service accounts, secret references
macOS Notes app: create/update/delete notes, folders, search, attachments, iCloud sync
macOS Reminders: create tasks, due dates, priorities, lists, location-based, iCloud sync
Bear: markdown notes, tags, themes, export, cross-note linking, Bear API/URL scheme
Content monitoring: new post detection, RSS feeds, web scraping triggers, change alerts
BluOS speaker control: play/pause/volume, multi-room audio, source selection, presets