openai-whisper-api

You can transcribe audio by providing the file path to this Skill, which sends the audio to the OpenAPI Audio Transcriptions API. It returns written text records of the spoken content.

Yes, you need an OpenAI API key for authentication and processing. The Skill uses this key to securely access the Whisper model and convert your spoken audio into text.

The Skill supports various audio formats for speech-to-text transcription. You can provide common audio files to generate accurate text output using the Whisper model.

Yes, you can specify the language of the audio for improved accuracy during transcription. This language specification helps the Whisper model better process the spoken content.

Yes, cURL is required as a dependency. The Skill uses cURL scripts to communicate with the OpenAI Audio Transcriptions API and retrieve your text output.

Yes, you can customize the output format by choosing between plain text or JSON. This allows you to select the structure that best fits your downstream text record needs.