Audio Transcription Tool

A web application written to accept an audio file, transcribe it using Google's Speech-to-Text API, and generate a downloadable Word document containing the transcription. It leverages Flask for the web server, Google Cloud Storage for storing audio files, and will soon use Google Cloud Firestore for managing metadata.

Key Components

• Flask Web Server: Manages file uploads and serves the generated Word documents.
• Google Cloud Storage (GCS): Stores the uploaded audio files.
• Google Speech-to-Text API: Performs the audio file transcriptions.
• python-docx: Generates Word documents from the transcription texts.

Setup and Deployment

Prerequisites

• Python 3.8 or later.
• A Google Cloud account.
• Flask installed in your Python environment.
• Google Cloud SDK installed for deployment purposes. [not necessary for running locally]

Local Development Setup

1. Clone this repository:

   git clone [email protected]:quarterlylearnings/reading-transcriber.git
   cd reading-transcriber

2. Install dependencies:

   pip install -r requirements.txt

3. Configure Google Cloud service account authentication:

   Set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of your Google Cloud service account key file.

   export GOOGLE_APPLICATION_CREDENTIALS="/path/to/your/service-account-file.json"

4. Run the application:

   flask run