whisper-audio-transcription

Sends a local audio file to the OpenAI speech-to-text endpoint and saves the transcript, choosing the model, spoken-language hint, recognition prompt and text or JSON output, with a dependency-free helper script and checks for the resulting file. Use when the user says "transcribe this recording", "convert a voice memo to text", "get a transcript of this interview audio", or asks for Whisper or /v1/audio/transcriptions. Not for local offline transcription models, real-time streaming speech recognition, or speaker diarization.

Version

v1.0.1

Size

10 KB

Updated

2026-10-06

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.