Audio transcript

A utility capable of recording speech from a microphone or accepting a ready audio file as input, after which it performs automatic transcription using a neural network model. The goal of the project is to simplify the process of obtaining text from audio, for example, for transcripts, interviews, notes, or automatic document preparation based on voice comments. Key requirements: ease of launch, command line support, stable operation, and integration of the OpenAI Whisper model.
Needed for the order:
Audio files for testing (if a sample needs to be checked) — optional
Preferences for the output text format (txt, json, time breakdown, etc.)
Clarification on whether only microphone recording, only audio files, or both options will be used
Operating system for which the build or instructions are required (Windows/Linux/Mac)
Language(s) of the audio (to select the appropriate Whisper model)