Writing & Content ✓ OpenAI · Official audio-transcriptionspeaker-diarizationopenai-apipython-cliknown-speaker-identification

Audio Transcribe

Turn audio or video speech into text with optional speaker labels.

FollowSkills review · FSRS-2.0
Not recommended
50/ 100 5-point scale 2.5 / 5
Trust15 / 25 · 3.0/5

The evidence shows that the skill uses an environment variable rather than asking users to paste an API key, and it documents audio, known-speaker references, and output paths. However, it uploads audio and speaker references to OpenAI, lacks per-run confirmation, minimization/retention guidance, privacy warnings, dependency pinning, and rollback, so points are deducted.

Reliability8 / 20 · 2.0/5

The script provides diagnosable checks for parameters, file existence, output conflicts, and some model constraints. However, there are no committed tests or execution records; files over 25 MB are warned about rather than rejected, API exception handling and batch-failure behavior are thin, and media compatibility boundaries are incomplete. The static ceiling therefore applies and points are deducted.

Adaptability9 / 15 · 3.0/5

Trigger scenarios, input files, text/JSON/diarized output, and known-speaker parameters are reasonably clear, and a language hint is supported. Non-fit boundaries, actual video support, Chinese-quality expectations, and mainland-China network reachability are not explained; the core function depends on an online OpenAI service, so points are deducted.

Convention8 / 15 · 2.7/5

The documentation is readable and layered, with workflow, decision rules, dependencies, environment requirements, examples, and a reference file. However, individual license metadata is unknown, versioning, changelog, maintenance ownership, and update path are unclear, and the repository README marks the repository as deprecated, so points are deducted.

Effectiveness6 / 15 · 2.0/5

The script can produce directly usable transcript text or JSON and supports diarization and known-speaker references. Static material contains no representative outputs or execution verification; quality validation remains user-dependent, and the agent default prompt promises a clean summary that the script itself does not produce. Only limited core-task credit is justified.

Verifiability4 / 10 · 2.0/5

The source code, validation logic, and payload construction are auditable, and the reference document partially corroborates the script. There is no test suite, CI coverage, third-party execution record, or multi-source corroboration, so only limited static verifiability is supported and points are deducted.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision 49f948faa925
Before you use it
  • This skill sends recordings and optional speaker references to OpenAI; obtain explicit authorization and confirm applicable data policies before processing sensitive or personal data.
  • Files over 25 MB only generate a warning and may still proceed toward the API; split them beforehand or add a hard rejection.
  • Mainland-China reachability, service availability, model availability, and current API compatibility are not verified by the supplied material.
  • The repository is marked deprecated; license status, maintenance ownership, and the future update path require separate confirmation.
Review evidence [1][2][3][4][5][6]
See the full review method →

What it does & when to use it

Audio Transcribe converts audio files into text through OpenAI transcription models and can add speaker diarization when requested. It uses a bundled Python CLI for repeatable runs and supports text, JSON, and diarized JSON outputs. Users may provide a language hint and known-speaker reference recordings. Live API calls require a locally configured OPENAI_API_KEY.

Collects audio paths, an output format, an optional language hint, and known-speaker references; verifies OPENAI_API_KEY; runs transcribe_diarize.py; defaults to gpt-4o-mini-transcribe with text output; switches to gpt-4o-transcribe-diarize with diarized_json for speaker labels; keeps chunking-strategy auto for audio longer than about 30 seconds; writes results to a specified file or output/transcribe/ directory; and checks transcription quality, speaker labels, and segment boundaries.

  1. A journalist converts an interview recording into plain text and saves it as transcript.txt.
  2. A meeting organizer needs speaker-labeled output and can provide reference recordings for up to four known speakers.
  3. A researcher processes recordings longer than about 30 seconds using automatic chunking.
  4. A team transcribes multiple files while using --out-dir to prevent output collisions.

Pros & cons

Pros
  • Supports text, JSON, and diarized_json output formats.
  • Accepts optional language hints, speaker labels, and known-speaker reference recordings.
  • Provides a repeatable CLI and separate output directories for multi-file jobs.
Limitations
  • Live calls require OPENAI_API_KEY and network access.
  • The documented known-speaker example supports up to four speakers.
  • Prompting is not supported for gpt-4o-transcribe-diarize.
  • The source does not provide a test suite, platform test results, or a separate license for this skill.

How to install

This skill is part of the curated skills in openai/skills. Install it from Codex with: $skill-installer transcribe. Restart Codex after installation so it can load the skill. The repository README also states that the repository is deprecated and points to the OpenAI Plugins repository for current examples.

How to use

Set OPENAI_API_KEY locally; never paste the key into chat. Set the paths: export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}" and export TRANSCRIBE_CLI="$CODEX_HOME/skills/transcribe/scripts/transcribe_diarize.py". Fast transcription: python3 "$TRANSCRIBE_CLI" path/to/audio.wav --out transcript.txt. Speaker-labeled transcription: python3 "$TRANSCRIBE_CLI" meeting.m4a --model gpt-4o-transcribe-diarize --known-speaker "Alice=refs/alice.wav" --known-speaker "Bob=refs/bob.wav" --response-format diarized_json --out-dir output/transcribe/meeting.

FAQ

Does the source document pricing?
No. It only states that live API calls require an OpenAI API key.
How should the API key be supplied?
Create and export OPENAI_API_KEY locally; the skill explicitly says not to request the full key in chat.
Why should results be reviewed?
The workflow requires checking transcription quality, speaker labels, and segment boundaries, with one targeted iteration if needed.
Which output formats are supported?
The documented formats are text, json, and diarized_json; use --out-dir for multiple files to avoid overwriting.

More skills from this repository

All from openai/skills

Productivity & Collaboration ✓ OpenAI · Official

Goal Definition Assistant

Turn vague intentions into measurable, verifiable goals with clear scope and stopping conditions.

Dev & Engineering ✓ OpenAI · Official

Codex CLI Builder

Turn APIs, scripts, and existing tools into durable, composable command-line interfaces.

Design & Frontend ✓ OpenAI · Official

Codex Image Studio

Generate and edit production-ready raster assets for projects.

Dev & Engineering ✓ OpenAI · Official

OpenAI Developer Docs Assistant

Current, official guidance for building with OpenAI products, APIs, and Codex.

Dev & Engineering ✓ OpenAI · Official

Skill Creator Guide

A practical guide to designing, writing, validating, and iterating reusable Codex skills.

Dev & Engineering ✓ OpenAI · Official

ASP.NET Core Engineering Guide

Guides developers through building, reviewing, and upgrading ASP.NET Core apps.

Dev & Engineering ✓ OpenAI · Official

ChatGPT Apps Builder

Build documented ChatGPT apps that pair an MCP server with a widget UI.

Design & Frontend ✓ OpenAI · Official

Figma Code Connect Mapper

Link Figma components to their code implementations for traceable design-code consistency.

Design & Frontend ✓ OpenAI · Official

Figma Blank File Creator

Create a blank Figma Design or FigJam file in the selected drafts folder.

Design & Frontend ✓ OpenAI · Official

Figma Design Implementer

Turn Figma specifications into production-ready frontend code with verifiable visual fidelity.

Dev & Engineering ✓ OpenAI · Official

Playwright Browser Automation Skill

Drive a real browser from the terminal for web interaction, extraction, and UI debugging.

Automation & Ops ✓ OpenAI · Official

Security Best Practices Review

Security review and secure-by-default guidance for Python, JavaScript/TypeScript, and Go projects.

Design & Frontend ✓ OpenAI · Official

Hatch Pet Animation Workshop

Turn character or brand cues into validated, packageable Codex animated pets.

Productivity & Collaboration ✓ OpenAI · Official

Linear Workflow Manager

Manage Linear tickets, projects, and team workflows directly through Codex.

Automation & Ops ✓ OpenAI · Official

Repository Threat Modeler

Builds evidence-grounded, actionable AppSec threat models for code repositories.

Automation & Ops ✓ OpenAI · Official

Sentry Production Error Explorer

Inspect Sentry issues, events, and basic production health through the Sentry CLI.

Design & Frontend ✓ OpenAI · Official

Figma Design System Rules Builder

Generates project-specific rules for consistent Figma-to-code implementation.

Design & Frontend ✓ OpenAI · Official

Figma Design System Builder

Build and validate a professional Figma design system from code.

Design & Frontend ✓ OpenAI · Official

Figma Design-to-Code Assistant

Fetch Figma design context and turn selected nodes into production code.

Data & Analysis ✓ OpenAI · Official

Jupyter Notebook Workflow Assistant

Create, refactor, and validate reproducible Jupyter notebooks with templates and a scaffold script.

Related skills