Transcribe (OpenAI Codex)
27,820 starsOfficial Codex speech-to-text skill: transcribe audio files with optional diarization and known-speaker hints — for interviews, meetings and recordings.
- First published：2025-11-25
- data as of：
- 2026-09-30
- Licence：
- None declared (see repository)
When to use it
When turning recordings or video audio into text, especially with speaker labels.
Caution
No license file in the repo; transcription typically relies on an external speech API or local model (paid or compute cost) — check the bundled scripts' configuration first.
Install prompt
請幫我安裝「Transcribe (OpenAI Codex)」技能：從 https://github.com/openai/skills/tree/main/skills/.curated/transcribe（技能路徑：skills/.curated/transcribe/） 取得完整的技能目錄，放進我的 Agent 的技能目錄（例如專案內的 skills/ 資料夾，或該 Agent 文件指明的全域技能位置），確認裡面的 SKILL.md 存在、frontmatter 的 name 與 description 完整，然後列出這個技能宣告的腳本、外部工具與 API 需求，先不要執行任何腳本。Paste this to your agent. It deliberately contains no tool subcommands — check the tool's official docs for commands.
Compatible with