Agent Wealth HubFree public resources
中文 EN العربية

Back to catalog / Developer tools

Audio transcription: transcribe and label speakers when needed

Use the bundled script and OpenAI API for one or more audio files.

Skills

Confirm audio or video paths, desired `text`, `json`, or `diarized_json` output, language hint, and any known-speaker references. Check that `OPENAI_API_KEY` is set locally; never request it in chat. Plain text with `gpt-4o-mini-transcribe` is the fast default. Use the diarization model and JSON only when speaker labels are requested, and choose `--chunking-strategy auto` for recordings longer than about 30 seconds. Run the bundled `transcribe_diarize.py`; use `--out-dir` for multiple files to avoid overwrites. Review transcription quality, speaker labels, and segment boundaries. Audio API processing may incur charges; save outputs under `output/transcribe/` and disclose any unverified parts.

Permissions

Prerequisites

Permissions

Limitations

Default to fast plain text for ordinary short audio; use diarized JSON only for speaker labels and auto-chunking beyond about 30 seconds.

Pinned upstream source

https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/skills/.curated/transcribe/SKILL.md

Repository
openai/skills
File path
skills/.curated/transcribe/SKILL.md
Pinned commit
49f948faa9258a0c61caceaf225e179651397431
Source checked
2026-10-14 · Reviewed against the pinned upstream source

Repository metrics

These values describe the upstream repository, not popularity or likes for an individual skill or playbook.

Stars
Not collected
Forks
Not collected
Observed at
Not collected

No metrics snapshot is available yet.

License: Apache-2.0

Compatible tools

bundled `scripts/transcribe_diarize.py` · OpenAI Python SDK

View skill directory

Main topic

Take a coding Agent change from context to verification

Related resources