Speech-to-Text Transcription App

This project is a web-based application that transcribes audio files into text using Azure Speech-to-Text SDK. It is built with Python, powered by Streamlit, and deployed on Heroku.

Features

• Upload audio files for transcription.
• Utilizes Azure Speech-to-Text SDK for accurate and fast transcriptions.
• Simple and user-friendly web interface created with Streamlit.
• Secure and scalable deployment on Heroku.

App Screenshot

Here's how the app looks:

---

Getting Started

Prerequisites

To run this project locally, ensure you have the following installed:

• Python 3.8 or later
• Azure Subscription to access the Speech-to-Text service
• Streamlit
• Azure SDK for Python

Installation

1. Clone the repository:

   git clone /~https://github.com/s-shahpouri/your-repo-name.git
   cd your-repo-name

2. Create and activate a virtual environment:

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install the required packages:

   pip install -r requirements.txt

4. Set up your .env file:

   • Create a .env file in the root directory.
   • Add your Azure Speech-to-Text key and region:

     AZURE_SPEECH_KEY=your_azure_key
     

---

Local Usage

1. Run the Streamlit app:

   streamlit run app.py

2. Open the provided URL in your browser (e.g., http://localhost:8501).

3. Upload an audio file and click the "Transcribe" button to see the transcription.

---

Deployment

1. Install the Heroku CLI and log in:

   heroku login

2. Create a Heroku app:

   heroku create your-app-name

3. Set your environment variables on Heroku:

   heroku config:set AZURE_SPEECH_KEY=your_azure_key AZURE_REGION=your_azure_region

4. Push your code to Heroku:

   git push heroku main

---

Built With

• Python - Programming language
• Streamlit - Web framework
• Azure Speech-to-Text SDK - Speech recognition
• Heroku - Deployment platform

---

Contributing

Contributions are welcome! Please fork the repository and create a pull request with your changes.

---

License

This project is licensed under the MIT License. See the LICENSE file for details.