Podcast generator

Podcast Generator is a lightweight desktop application designed to transform text scripts into multi-speaker podcasts using the Google Gemini text-to-speech API. Developed in Python with Tkinter, this tool offers a user-friendly interface and a range of features to enhance podcast creation.

Benefits

Podcast Generator boasts several key features:-Audio Generation: Create multi-speaker podcasts with high-quality voices from the Google Gemini API.-User-Friendly Interface: An intuitive graphical interface built with Tkinter.-Flexible Formats: Export podcasts in MP3 (default) or WAV formats.-Customization: Configure and save voices for each speaker, with options for language and accent.-Integrated Playback: Listen to and stop audio playback directly from the application (requires FFmpeg).-Secure API Key Storage: Your Google Gemini API key is securely stored in your system's keychain.-Automatic Versioning: The application version is synchronized with the project's Git tags.

Use Cases

Podcast Generator is versatile and can be used for:-Teaching and Training: Transform course materials or tutorials into multilingual audio podcasts.-Content Creation: Automate the production of podcasts in various languages to reach a broader audience.-Accessibility: Make content accessible to a wider audience through multilingual support.-Language Practice: Create multilingual dialogues with distinct voices for each character.

Installation

1. External Dependency: FFmpeg (Required)

For audio conversion and playback, FFmpeg must be installed on your system.

macOS

Install via Homebrew:

brew install ffmpeg

Linux

Most distributions provide FFmpeg in their package manager:

sudo apt install ffmpeg # Debian/Ubuntusudo dnf install ffmpeg # Fedorasudo pacman -S ffmpeg # Arch

Windows

1. Download FFmpeg: Go to the official FFmpeg build page and download the latest "release full" ZIP archive.
2. Extract the archive: Right-click the downloaded ZIP file and choose **Extract All