openai-whisper-api

Transcribe audio files using OpenAI's Whisper API by running a curl script that calls the /v1/audio/transcriptions endpoint. You need an OPENAI_API_KEY, and optionally an OPENAI_BASE_URL, to generate text or JSON transcripts.

Yes, you can use curl to transcribe podcasts and meeting audio via the Whisper API. The script targets the /v1/audio/transcriptions endpoint, converting your audio recordings into searchable, editable text without manual typing.

Yes, you need an OPENAI_API_KEY to transcribe audio. You can also set an optional OPENAI_BASE_URL to route the curl request through a local or proxy gateway, enabling integration into custom automation workflows.

Whisper transcription supports various audio formats and languages. You can specify the language and use optional prompts when sending your audio file to the API, choosing either text or JSON output formats to fit downstream pipelines.

Automate audio transcription by integrating the curl-based transcription script into your workflow. Point the script to a local or proxy gateway via OPENAI_BASE_URL, and output text or JSON formats to seamlessly pass transcripts to downstream applications.