In brief
Transcribed audio into text, with optional distinction of speakers and clues on known speakers: interviews, meetings, recordings.
What it does
- Audio and video transcript
- Identify speakers
Install
In Codex: $skill-installer transcribe, then restart Codex (README).
$skill-installer transcribeWorks with
- Codex
Source: README : Codex skills catalogue.
Level: Beginner
Suppose to write code that calls an API and to manage a key to the API.
SKILL.md excerpt
The original description, which the agent reads to decide whether to load the skill (in English):
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
Quoted from SKILL.md at commit 49f948f . The folder also contains 5 extra files (agents/, assets/, references/, scripts/).
The SKILL.md has 82 lines and 8 main sections:
- Workflow
- Decision rules
- Output conventions
- Dependencies (install if missing)
- Environment
- Skill path (set once)
- CLI quick start
- Reference map
Licence: Apache 2.0
Checked on 10 November 2026 : licence file in the skill folder .
Compatible licence, but the skill is deprecated (page not indexed): full text not reproduced.
In the directory
Use cases and guides that share a theme, industry or tool with this skill.
Comments.
A field note, a question, a precision on this skill? Comments are reviewed before publication.
Published comments
Loading comments…
Leave a comment
Moderation charter. Every comment is reviewed before publication. We refuse hate speech, insulting or discriminatory language, advertising, spam and promotional links, off-topic posts and other people’s personal data.