first commit

podcast-tts-generator/README.md

@@ -0,0 +1,52 @@
+# Podcast TTS Generator
+
+## Overview
+The Podcast TTS Generator is a Python application that automates the process of generating text-to-speech output for podcasts. It takes prompts from text files, generates detailed outlines using the ChatGPT API, creates scripts from those outlines, and finally synthesizes speech to produce audio files.
+
+## Project Structure
+```
+podcast-tts-generator
+├── src
+│   ├── main.py               # Entry point of the application
+│   ├── chatgpt_api.py        # Functions to interact with the ChatGPT API
+│   ├── outline_generator.py    # Class to create outlines from prompts
+│   ├── script_creator.py      # Class to generate scripts from outlines
+│   ├── tts_engine.py          # Class to synthesize speech from scripts
+│   └── utils.py               # Utility functions for file handling
+├── prompts
+│   └── sample_prompt.txt      # Sample text prompt for testing
+├── outputs
+│   ├── outlines               # Directory for generated outlines
+│   ├── scripts                # Directory for generated scripts
+│   └── audio                  # Directory for generated audio files
+├── requirements.txt           # Project dependencies
+└── README.md                  # Project documentation
+```
+
+## Installation
+1. Clone the repository:
+   ```
+   git clone <repository-url>
+   cd podcast-tts-generator
+   ```
+
+2. Install the required dependencies:
+   ```
+   pip install -r requirements.txt
+   ```
+
+## Usage
+1. Place your text prompts in the `prompts` directory. You can use the provided `sample_prompt.txt` as a template.
+   
+2. Run the application:
+   ```
+   python src/main.py
+   ```
+
+3. The generated outlines, scripts, and audio files will be saved in the respective directories under `outputs`.
+
+## Contributing
+Contributions are welcome! Please feel free to submit a pull request or open an issue for any enhancements or bug fixes.
+
+## License
+This project is licensed under the MIT License. See the LICENSE file for more details.

podcast-tts-generator/prompts/sample_prompt.txt

@@ -0,0 +1,3 @@
+This file contains a sample text prompt that will be used to test the functionality of the application.
+
+Welcome to our podcast! In this episode, we will explore the fascinating world of artificial intelligence and its impact on our daily lives. We'll discuss the latest advancements, ethical considerations, and what the future holds for AI technology. Join us as we dive deep into this exciting topic!

podcast-tts-generator/src/chatgpt_api.py

@@ -0,0 +1,17 @@
+import openai
+import os
+
+# Load your OpenAI API key from an environment variable or directly
+API_KEY = os.getenv("OPENAI_API_KEY")
+
+openai.api_key = API_KEY
+
+def generate_outline(prompt: str) -> str:
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "user", "content": prompt}
+        ]
+    )
+    outline = response.choices[0].message['content']
+    return outline.strip()

podcast-tts-generator/src/main.py

@@ -0,0 +1,33 @@
+import os
+from chatgpt_api import generate_outline
+from outline_generator import OutlineGenerator
+from script_creator import ScriptCreator
+from tts_engine import TTSEngine
+from utils import read_prompt, save_output
+
+def main():
+    # Define paths
+    prompt_file_path = 'prompts/sample_prompt.txt'
+    outline_output_path = 'outputs/outlines/outline.txt'
+    script_output_path = 'outputs/scripts/script.txt'
+    audio_output_path = 'outputs/audio/output.mp3'
+
+    # Read prompt from file
+    prompt = read_prompt(prompt_file_path)
+
+    # Generate outline
+    outline_generator = OutlineGenerator()
+    outline = outline_generator.create_outline(prompt)
+    save_output(outline_output_path, outline)
+
+    # Generate script from outline
+    script_creator = ScriptCreator()
+    script = script_creator.generate_script(outline)
+    save_output(script_output_path, script)
+
+    # Convert script to speech
+    tts_engine = TTSEngine()
+    tts_engine.synthesize_speech(script, audio_output_path)
+
+if __name__ == '__main__':
+    main()

podcast-tts-generator/src/outline_generator.py

@@ -0,0 +1,7 @@
+class OutlineGenerator:
+    def __init__(self, chatgpt_api):
+        self.chatgpt_api = chatgpt_api
+
+    def create_outline(self, prompt: str) -> str:
+        outline = self.chatgpt_api.generate_outline(prompt)
+        return outline

podcast-tts-generator/src/script_creator.py

@@ -0,0 +1,4 @@
+class ScriptCreator:
+    def generate_script(self, outline: str) -> str:
+        script = f"Welcome to our podcast! Today, we will discuss the following topics:\n\n{outline}\n\nThank you for listening!"
+        return script

podcast-tts-generator/src/tts_engine.py

@@ -0,0 +1,16 @@
+class TTSEngine:
+    def synthesize_speech(self, script: str, output_file: str) -> None:
+        import pyttsx3
+
+        # Initialize the text-to-speech engine
+        engine = pyttsx3.init()
+
+        # Set properties before adding anything to speak
+        engine.setProperty('rate', 150)    # Speed percent (can go over 100)
+        engine.setProperty('volume', 1)     # Volume 0-1
+
+        # Save the speech to a file
+        engine.save_to_file(script, output_file)
+
+        # Wait for the speech to finish
+        engine.runAndWait()

podcast-tts-generator/src/utils.py

@@ -0,0 +1,7 @@
+def read_prompt(file_path: str) -> str:
+    with open(file_path, 'r') as file:
+        return file.read()
+
+def save_output(file_path: str, content: str) -> None:
+    with open(file_path, 'w') as file:
+        file.write(content)