Textify

Welcome to the Speech To Text repository! This allows to actively record, transcribe and summerize online meetings by the use of AI and langchain audience description.

Table of Contents

• Installation
• Usage
• Contributing
• License

Installation

To get started with this project, follow the steps below:

1. Clone the repository:

git clone https://github.com/blackhammer/Textify.git

2. Navigate to the project directory:

cd Textify

3. Install the required dependencies:

pip install -r requirements.txt

4. Move onto the frontend's directory

cd SpeechToText

5. Install the required dependencies:

npm install

Usage

To run the project, use the following command:

cd SpeechToText

npm run dev

This will spin up the frontend. if you get the following error:

Error: The following dependencies are imported but could not be resolved:
                        react-mic (imported by Textify/SpeechToText/src/components/ReactRecorder.jsx)
                        axios (imported by Textify/SpeechToText/src/components/ReactRecorder.jsx)
                        Are they installed?

Run the following command

npm install axios react-mic --legacy-peer-deps

Then spin up the backend

cd ..

python app.py

Be sure to use your OWN COHERE API for this app otherwise it wont work

Once the server is up and running, you can access the application at http://localhost:5000.

Contributing

If you'd like to contribute, feel free to fork the repository and submit a pull request. Please make sure to follow the following guidelines:

• Write clear, concise commit messages
• Follow the code style and formatting conventions
• Ensure all tests pass before submitting a PR

License

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