openai-whisper-api

Transcribe audio to text using OpenAI Whisper by running a curl-based client that calls the /v1/audio/transcriptions endpoint. It processes podcast, meeting, and media audio files, outputting plain text or JSON for quick text availability.

Yes, the curl-based transcription client supports optional --model, --language, and --prompt parameters. It utilizes the whisper-1 model by default and allows you to specify language to optimize automated transcription across languages.

Automate podcast transcription by passing your podcast audio file to the Whisper API curl script. It converts media workflows into searchable transcripts, outputting JSON or plain text for accessibility and archiving.

Yes, curl is a required dependency. The Skill functions as a curl-based client that calls OpenAI's /v1/audio/transcriptions endpoint to process audio workflows.

Yes, the Whisper API transcription supports JSON output. It provides automated transcription of audio files into readable text with optional JSON formatting to suit different media workflow requirements.

Use the --prompt parameter during audio transcription to provide context to the OpenAI Whisper model. It helps guide the automated transcription process for meetings, podcasts, and other media workflows requiring accurate text availability.