transcribe

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.

Try your first task

Transcribe one recording to plain text

Start a fresh conversation. Replace the highlighted placeholders.

Use the transcribe skill to transcribe `[path/to/audio.wav]` as plain text and save it to `[path/to/transcript.txt]`. Use the fast default transcription mode without speaker diarization, then report any obvious quality concerns.

Required inputs

Replace `[path/to/audio.wav]` with an audio or video file path
Replace `[path/to/transcript.txt]` with the desired output path
Set `OPENAI_API_KEY` locally without pasting it into chat
Install the `openai` Python package if it is missing

Suggested template by Skill Leaderboard, grounded in the linked source. Task evidence ↗

Inside SKILL.md

81 lines

Section content has not been verified for this skill yet.

Full source remains withheld under the current source-display policy. Read the author’s source ↗