skilld
All skills
openai avatar

/transcribe

@0ed635a official
by openaiopenai/skills28k stars
1,891

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.

Ask your Agent

Use this Skill: https://skilld.dev/gh/openai/skills/transcribe

This session only. Nothing lands on disk.

referencesapi.md

≈115 tokens on demand. Your agent reads this file only when SKILL.md points to it.

gpt-4o-transcribe-diarize quick reference

  • Input formats: mp3, mp4, mpeg, mpga, m4a, wav, webm.
  • Max file size: 25 MB per request.
  • response_format options: text, json, diarized_json.
  • For audio longer than ~30 seconds, pass chunking_strategy (use "auto" to split into chunks).
  • Known speakers: up to 4 references via extra_body known_speaker_names + known_speaker_references (data URLs).
  • Prompting is not supported for gpt-4o-transcribe-diarize.

Source: SKILL.md on GitHub

Third-party checks

1 warning17d5 checks · Risk SAFE
  • Gen Agent Trust Hub17d

    This skill provides functionality to transcribe audio files with optional speaker diarization using the official OpenAI API. The implementation follows standard practices for dependency management and credential safety.

  • Socket17d

    No alerts

  • Snyk17d

    Risk: LOW · No issues

  • Runlayer7mo

    5/5 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 0ed635a. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Activeupdated 8 months ago

Topics

README badge

README badge for openai/skills/transcribe

What it does

Transcribes audio files to text using OpenAI's Whisper API, with optional speaker diarization and known-speaker hints via a bundled Python CLI. Use when extracting speech-to-text from recordings, interviews, or meetings where speaker labels are needed.

Generated from the current SKILL.md.

Frequently asked

What transcription models does this skill use?
By default, gpt-4o-mini-transcribe for fast text transcription. For speaker diarization and labeling, use gpt-4o-transcribe-diarize, which does not support prompting.
Does this skill support speaker diarization?
Yes. Pass --model gpt-4o-transcribe-diarize and --response-format diarized_json. You can also provide known-speaker audio references to label specific speakers in interviews or meetings.
What audio formats are supported?
The skill supports common formats including WAV, M4A, and MP3. See references/api.md for the full list of supported formats and size limits.
What do I need to set up before using this skill?
Set the OPENAI_API_KEY environment variable by creating a key in the OpenAI platform UI and exporting it in your shell. The skill requires the openai Python package, installed via uv or pip.

Generated from the current SKILL.md. These answers refresh after source changes.