Transcription is the process of converting spoken words in audio files into written text. This task is crucial for making audio content accessible, searchable, and analyzable.

Running Transcription with supercontrast is simple. You need to provide the audio file (either as a URL or a local file path) and specify the provider you want to use. In this example, we’ll use Task.TRANSCRIPTION with Provider.OPENAI, which utilizes OpenAI’s Whisper API.

from supercontrast import SuperContrastClient, Task, Provider, TranscriptionRequest

client = SuperContrastClient(task=Task.TRANSCRIPTION, providers=[Provider.OPENAI])
request = TranscriptionRequest(audio_file="https://github.com/supercontrast-ai/supercontrast/raw/main/tests/audio/test_transcription.wav")
response, metadata = client.request(request)

Each task has its own request and response schema. For Task.TRANSCRIPTION, the request schema is defined by TranscriptionRequest and the response schema is defined by TranscriptionResponse.

TranscriptionRequest

  • audio_file: a string that can be either a URL to an audio file or a local file path.

TranscriptionResponse

  • text: a string containing the transcribed text from the audio file.
Translation