Radio Imaging Audio Generator Development

Bilel

Bilel Aroua

๐ŸŒŸRadio Imaging Audio Generator

๐Ÿ“œDescription

The Radio Imaging Audio Generator is a Streamlit-based application designed for radio producers and music creators. It combines OpenAI's GPT models with Facebook's MusicGen technology, enabling the generation of unique audio pieces from user-provided prompts.

๐ŸŒ Project Continuation and User Involvement

This app is the next step in our project, following the Custom GPT Radio Imaging and MusicGen AI. It's tailored for radio producers and music creators, offering new levels of creativity and efficiency. [GPT] (https://chat.openai.com/g/g-65x53n87E-radio-imaging-musicgen-ai)

๐Ÿš€ Features

Text-prompt-based audio generation for radio imaging.
Integration with OpenAI's GPT and Facebook's MusicGen models.
User-friendly interface for inputting prompts and API keys.
Direct audio playback and download options within the app.
๐Ÿ‘ฅ How You Can Contribute
Feedback: Share your experiences and improvement suggestions.
Use Cases: Tell us about your process using the app.
Spread the Word: Help others discover and use this tool.

๐Ÿ›  Installation

Requirements

Python 3.x
Streamlit
Transformers
SciPy
TensorFlow
PyTorch
OpenAI API key

Setup

Clone the repository.
Install required packages: pip install -r requirements.txt
Run the app: streamlit run app.py

Usage

Launch the Streamlit app.
Enter your OpenAI API key.
Select an OpenAI chat model.
Input a description for the audio piece.
Click 'Generate Audio'.
Listen and download the audio directly in the app.

๐ŸŒ Access the Application

Experience the Radio Imaging Audio Generator now: Access the Streamlit App here. https://radio-imaging-audio-generator.streamlit.app/

How to Use This Web App?

To get started with creating your unique audio pieces, follow these simple steps: 1. Enter OpenAI API Key
In the sidebar, input your OpenAI API key. This is essential to access the GPT model for generating audio descriptions.
Don't have an API key? Get one for free here. 2. Select GPT Model
Choose the desired GPT model from the dropdown in the sidebar. We recommend using 'gpt-3.5-turbo-16k' for more detailed and rich descriptions. 3. Input Your Detailed Description
Describe your audio idea in the text area provided. Be as detailed as possible to guide the AI effectively. This could include the mood, style, specific instruments, or any other relevant details. 4. Generate and Review the Prompt
Click on ' Generate Prompt' to create a descriptive prompt for your audio. Review it to ensure it aligns with your vision. 5. Generate Your Audio
If you're satisfied with the prompt, hit 'โ–ถ Generate Audio'. This will process your request and create the audio piece based on the AI-generated description. 6. Playback and Download
Once generated, you can play the audio directly within the app. If it meets your needs, feel free to download and use it in your projects.

Thank you for your interest!
Bilel Aroua

๐Ÿ’ฌ Contact

Like this project

Posted Sep 19, 2025

Developed a Streamlit app for AI-based audio generation for radio and music.