Skill / OpenAI

Transcribe Codex Skill

Transcribe audio files to text with optional diarization and known-speaker hints.

Docs reviewedChecked 2026-09-20Runtime not tested

What it adds

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.

media and content

Get set up

Ask Codex to install the skill with the built-in skill installer, pointing it at the source below.
Start a new thread so Codex picks up the skill.

$skill-installer transcribe

Review before running

Read the installation source

Before you install

Compatibility & limitations

Documented for ChatGPT desktop app, Codex CLI, Codex IDE extension

Cursor: Not confirmed for Cursor.

This listing is based on source documentation. We have not installed or runtime-tested this asset.

How it fits together

PDF · SkillUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging...Diagnosing Superpowers · SkillUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill...Algorithmic Art · SkillCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration.Canvas Design · SkillCreate beautiful visual art in .png and .pdf documents using design philosophy.ChatCut · PluginInstall and connect ChatCut.Creative Production · PluginCreate marketing visuals from a brief or product image.Higgsfield · PluginEvery image and video model.

Sources & provenance

Reviewed 2026-09-20. Source revision: main (mutable; commit not pinned).