openai-whisper-api

Overview: Transcribe audio files using OpenAI’s Whisper API, a powerful speech-to-text tool. This skill requires an OpenAI API key for authentication.

Key Features:

• Transcribes audio files in various formats (e.g., .m4a, .ogg)
• Supports multiple models and languages
• Customizable output and prompt options

How It Works: This skill uses the curl binary to send a POST request to OpenAI’s /v1/audio/transcriptions endpoint, passing the audio file and optional parameters. The response is then parsed and output in the desired format.

Use Cases:

• Transcribe podcasts or lectures for note-taking or research
• Convert audio files to text for accessibility or search purposes
• Use as a starting point for more advanced NLP tasks, such as sentiment analysis or named entity recognition