This is a Python application that accepts text input (via URL, text, or file), uses OpenAI's GPT-4 Turbo model to generate a response based on the prompt, and then converts the generated text to speech using Azure's Text-to-Speech API. The app is built with streamlit for an intuitive web interface.
- OpenAI API Key: Obtain from OpenAI's website.
- Azure API Key: Obtain from Azure's website.
- Libraries: Install the necessary libraries using pip:
pip install requests streamlit openai beautifulsoup4 python-dotenv
-
Clone the Repository:
git clone https://github.com/hipnologo/openai_azure_text2speech.git cd openai_azure_text2speech -
Configure Environment Variables: Create a
.envfile in the project root and add your API keys:OPENAI_API_KEY=YOUR_OPENAI_API_KEY AZURE_API_KEY=YOUR_AZURE_API_KEY -
Run the Application: Launch the app using Streamlit:
streamlit run app.py
-
Input Options:
- Choose an input method (URL, direct text input, or file upload).
-
Customize Prompt Length:
- Use the slider to set the character limit (up to 5000 tokens).
-
Generate and Play Text-to-Speech:
- Generated text will display in the interface.
- Play the audio using the built-in audio player or download it by clicking the "Download" button.
- Multi-Input Options: Accepts URLs, text input, or text files.
- Voice Selection: Choose between
en-US-AriaNeural,en-US-GuyNeural, anden-GB-RyanNeuralvoices for Azure TTS. - OpenAI GPT-4 Turbo Model: Uses the latest model for better responses.
- Customizable Token Limit: Limit the response length to suit your requirements.
- Audio Download: Easily download the generated audio file in WAV format.
We welcome contributions! To contribute:
- Fork the repository.
- Create a branch for your feature or bug fix.
- Make and test your changes.
- Submit a pull request.
For a detailed guide, please refer to our CONTRIBUTING.md file.
Make sure to follow the coding style and add test cases for any new code. Feel free to reach out if you have any questions.
