Transkri

Transkri is a Python library designed for transcribing audio files into text. It aims to provide a user-friendly interface for accessing and utilizing various speech-to-text engines. The library supports multiple transcription services, including but not limited to, Whisper, Google Cloud Speech-to-Text, and AssemblyAI.

The primary function of Transkri is to simplify the process of converting spoken language from audio sources like WAV, MP3, or FLAC files into written text. Users can specify the audio file path and the desired transcription service as input. The library then handles the communication with the chosen service, sending the audio data and receiving the transcribed text.

Key features of Transkri include its ability to handle different audio formats and its support for a range of transcription backends. This flexibility allows users to choose the service that best suits their needs in terms of accuracy, cost, and language support. The library also aims to abstract away the complexities of interacting directly with individual API endpoints, offering a unified approach to transcription tasks. Transkri is intended for developers who need to integrate speech-to-text capabilities into their Python applications for purposes such as voice note summarization, automated captioning, or data analysis of spoken content.