openai-whisper-api

To transcribe audio to text using the OpenAI Whisper API, run the provided script with your audio file and an OPENAI_API_KEY. The process uses curl for HTTP requests to generate accurate transcripts.

Yes, you need an OpenAI API key to transcribe audio files. The OPENAI_API_KEY environment variable is required for authenticating the curl HTTP requests sent to the Whisper API endpoint.

Yes, you can get JSON output when transcribing podcasts or lectures by passing the --json flag. You can also use the --out flag to control other output formats for your transcripts.

Yes, the Whisper transcription script supports model selection and language specification. You can use the --model and --language flags respectively to control the transcription output.

The OpenAI Whisper transcription script requires curl as its only dependency. This command-line tool handles the HTTP requests needed to send audio data to the OpenAI API.