This repository contains a simple yet powerful tool for converting text scripts into voice narrations using OpenAI's GPT model. The application is built with Streamlit, allowing for an easy-to-use interface where users can input their text and generate voice narrations in MP3 format. Whether you're creating content, need assistance with reading, or exploring text-to-speech technologies, this tool is designed to be accessible and straightforward.
- Text Input: Users can input any text script into the provided text area.
- Voice Generation: With the click of a button, the application generates a voice narration of the input text.
- MP3 Download: Users can download the generated narration as an MP3 file.
- Generate .srt file for the generated audio
- Ask AI to generate audio based on text draft
- Add a feature to generate audio based on a video
To get started with the Text to Voice Converter, follow these steps:
- Python 3.9 or later
- An OpenAI API key
-
Clone the Repository
-
Set Up a Virtual Environment (Optional but recommended)
python -m venv venv source venv/bin/activate # On Windows use `venv\Scripts\activate`
-
Install Dependencies
pip install -r requirements.txt
-
Set Up Environment Variables
Create a
.secrets.tomlfile in the.streamlitdirectory of the project and add your OpenAI API key:OPENAI_API_KEY=your_openai_api_key_here
After completing the installation steps, you can run the application using Streamlit:
streamlit run main.pyOpen the link provided by Streamlit in your web browser, and you'll be greeted with the Text to Voice Converter interface.
- Enter Your Text: Type or paste the text you want to convert into the text area.
- Generate Voice: Click the "Generate Voice" button to create the voice narration of your text.
- Download MP3: After the voice has been generated, a download button will appear. Click it to download the MP3 file to your device.