### FastAPI Setup for Podcastfy

Source: https://github.com/souzatharsis/podcastfy/blob/main/README.md

This snippet indicates the setup for a FastAPI service for Podcastfy, suggesting containerization with Docker and providing an example of how to make API requests.

```python
Containerize podcastify and launch the api
Dockerfile_api

Make requests to the api look at the notebook for a clear example
fetch_audio(request_data, ENDPOINT, BASE_URL)
```

--------------------------------

### Setup and Run TinyLlama Local LLM

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/local_llm.md

This bash script demonstrates downloading a llamafile, making it executable, and starting the local LLM server. It listens at http://localhost:8080 by default.

```bash
# Download a llamafile from HuggingFace
wget https://huggingface.co/jartine/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile

# Make the file executable. On Windows, instead just rename the file to end in ".exe".
chmod +x TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile

# Start the model server. Listens at http://localhost:8080 by default.
./TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile --server --nobrowser
```

--------------------------------

### Clone Repository and Start Development Environment

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

Clone the Podcastfy repository and start the development environment using Docker Compose.

```bash
git clone https://github.com/souzatharsis/podcastfy.git
cd podcastfy
docker-compose up podcastfy-dev
```

--------------------------------

### Check Development Setup

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

Execute a command within the development Docker Compose environment to check the Podcastfy setup.

```bash
docker-compose exec podcastfy-dev python3 -c "import podcastfy"
```

--------------------------------

### Install Sphinx

Source: https://github.com/souzatharsis/podcastfy/blob/main/GUIDELINES.md

Install Sphinx, the documentation generator used by the project.

```bash
pip install sphinx
```

--------------------------------

### Install Gradio Client Library

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/api.md

Install the necessary Python library to interact with Gradio-based APIs.

```bash
pip install gradio_client
```

--------------------------------

### Install Docker Compose on Linux

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

Download and install the Docker Compose binary for Linux systems.

```bash
# Download the current stable release
sudo curl -L "https://github.com/docker/compose/releases/download/v2.24.1/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose

# Apply executable permissions
sudo chmod +x /usr/local/bin/docker-compose

# Verify installation
docker-compose --version
```

--------------------------------

### Verify Docker Installation (General)

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

A set of commands to verify the installation of Docker and Docker Compose, and test Docker functionality.

```bash
# Check Docker version
docker --version

# Check Docker Compose version
docker-compose --version

# Verify Docker daemon is running
docker ps

# Test Docker functionality
docker run hello-world
```

--------------------------------

### Install Poetry

Source: https://github.com/souzatharsis/podcastfy/blob/main/GUIDELINES.md

Install Poetry, the preferred dependency manager for this project.

```bash
pip install poetry
```

--------------------------------

### Example Output Result from API

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/api.md

This is an example of the server-sent event data received when a podcast generation is complete. It includes the file path and a downloadable URL.

```text
event: complete
data: [{"path": "/tmp/gradio/bcb143f492b1c9a6dbde512557541e62f090bca083356be0f82c2e12b59af100/podcast_81106b4ca62542f1b209889832a421df.mp3", "url": "https://thatupiso-podcastfy-ai-demo.hf.space/gradio_a/gradio_api/file=/tmp/gradio/bcb143f492b1c9a6dbde512557541e62f090bca083356be0f82c2e12b59af100/podcast_81106b4ca62542f1b209889832a421df.mp3", "size": null, "orig_name": "podcast_81106b4ca62542f1b209889832a421df.mp3", "mime_type": null, "is_stream": false, "meta": {"_type": "gradio.FileData"}}]
```

--------------------------------

### Install IPython Package

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

Installs the IPython package using pip, which is required for embedding audio in notebooks.

```shell
%pip install ipython
```

--------------------------------

### Verify Docker Installation (Windows/macOS)

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

Command to verify the Docker installation by checking its version.

```bash
docker --version
```

--------------------------------

### Verify Podcastfy Installation

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

Verify the Podcastfy installation by checking if the package can be imported in a bash environment.

```bash
python3 -c "import podcastfy"
```

--------------------------------

### Enable Docker Service on Boot (Linux)

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

Commands to configure Docker and containerd services to start automatically on system boot.

```bash
sudo systemctl enable docker.service
sudo systemctl enable containerd.service
```

--------------------------------

### Setup Local LLM Server with Llamafile

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

This bash script demonstrates downloading, making executable, and running a llamafile for a local LLM server. It defaults to listening on http://localhost:8080.

```bash
# Download a llamafile from HuggingFace
wget https://huggingface.co/jartine/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile

# Make the file executable. On Windows, instead just rename the file to end in ".exe".
chmod +x TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile

# Start the model server. Listens at http://localhost:8080 by default.
./TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile --server --nobrowser

```

--------------------------------

### Check cURL Installation

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/api.md

Verify that cURL is installed on your system by checking its version.

```bash
curl --version
```

--------------------------------

### Install Docker Engine on Ubuntu/Debian

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

Commands to install Docker Engine, CLI, and Compose plugin on Ubuntu/Debian systems.

```bash
# Remove old versions
sudo apt-get remove docker docker-engine docker.io containerd runc

# Install prerequisites
sudo apt-get update
sudo apt-get install \
    ca-certificates \
    curl \
    gnupg \
    lsb-release

# Add Docker's official GPG key
sudo mkdir -p /etc/apt/keyrings
curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg

# Set up repository
echo \
  "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu \
  $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

# Install Docker Engine
sudo apt-get update
sudo apt-get install docker-ce docker-ce-cli containerd.io docker-compose-plugin

# Add your user to docker group (optional, to run docker without sudo)
sudo usermod -aG docker $USER
newgrp docker

# Verify installation
docker --version
```

--------------------------------

### Pull and Start Podcastfy Container

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

Pull the latest production image and start the Podcastfy service using Docker Compose.

```bash
docker pull ghcr.io/souzatharsis/podcastfy:latest
docker-compose up podcastfy
```

--------------------------------

### Select ElevenLabs TTS Model

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

Demonstrates how to select a specific Text-to-Speech model for podcast generation. This example uses the ElevenLabs model.

```python
audio_file = generate_podcast(urls=["https://en.wikipedia.org/wiki/Podcast"], tts_model="elevenlabs")
```

--------------------------------

### API Key Setup and Validation

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

This Python script imports necessary libraries, defines required API keys (Google, OpenAI, ElevenLabs) from environment variables, and validates their presence. It raises a ValueError if any keys are missing.

```python
import requests
import json
import os
from pathlib import Path
import os

# Define required API keys
API_KEYS = {
    "GOOGLE_API_KEY": os.getenv("GOOGLE_API_KEY"),
    "OPENAI_API_KEY": os.getenv("OPENAI_API_KEY"),
    "ELEVENLABS_API_KEY": os.getenv("ELEVENLABS_API_KEY"),
}

# Validate API keys
missing_keys = [key for key, value in API_KEYS.items() if not value]

if missing_keys:
    raise ValueError(f"Missing API keys: {', '.join(missing_keys)}. Ensure they are set in environment variables.")

# Use API keys
GOOGLE_KEY = API_KEYS["GOOGLE_API_KEY"]
OPENAI_KEY = API_KEYS["OPENAI_API_KEY"]
ELEVENLABS_KEY = API_KEYS["ELEVENLABS_API_KEY"]


print("API keys successfully loaded.")

```

--------------------------------

### Generate podcast from PDF (commented out)

Source: https://github.com/souzatharsis/podcastfy/blob/main/usage/examples.ipynb

A commented-out example showing how to generate a podcast from a PDF file using the generate_podcast function. This snippet is not active.

```python
#audio_file = generate_podcast(urls=["../data/pdf/s41598-024-58826-w.pdf"], 
#                              tts_model="geminimulti")
```

--------------------------------

### Clone Repository

Source: https://github.com/souzatharsis/podcastfy/blob/main/GUIDELINES.md

Clone your forked repository locally to start making changes.

```bash
git clone https://github.com/your-username/podcastfy.git
```

--------------------------------

### Initiate Podcast Generation and Fetch Results

Source: https://github.com/souzatharsis/podcastfy/blob/main/usage/api.md

This operation involves two steps: first, a POST request to initiate podcast processing, which returns an EVENT_ID. Second, a GET request using the obtained EVENT_ID to fetch the generated podcast results. A delay of 1-3 minutes is expected between these steps.

```APIDOC
## POST /gradio_api/call/process_inputs

### Description
Initiates the podcast generation process by sending input data to the API. Returns an EVENT_ID that is used to track and retrieve the results.

### Method
POST

### Endpoint
https://thatupiso-podcastfy-ai-demo.hf.space/gradio_api/call/process_inputs

### Parameters
#### Request Body
- **data** (array) - Required - An array containing the input parameters for podcast generation in the following order:
  - **text_input** (string) - Direct text input for podcast generation
  - **urls_input** (string) - URLs to process (include http:// or https://)
  - **pdf_files** (array) - List of PDF files to process
  - **image_files** (array) - List of image files to process
  - **gemini_key** (string) - Google Gemini API key
  - **openai_key** (string) - OpenAI API key
  - **elevenlabs_key** (string) - ElevenLabs API key
  - **word_count** (number) - Target word count for podcast
  - **conversation_style** (string) - Conversation style descriptors (e.g. "engaging,fast-paced")
  - **roles_person1** (string) - Role of first speaker
  - **roles_person2** (string) - Role of second speaker
  - **dialogue_structure** (string) - Structure of dialogue (e.g. "Introduction,Content,Conclusion")
  - **podcast_name** (string) - Name of the podcast
  - **podcast_tagline** (string) - Podcast tagline
  - **tts_model** (string) - Text-to-speech model ("gemini", "openai", "elevenlabs", or "edge")
  - **creativity_level** (number) - Level of creativity (0-1)
  - **user_instructions** (string) - Custom instructions for generation

### Request Example
```json
{
  "data": [
    "text_input",
    "https://yourwebsite.com",
    [],
    [],
    "gemini_key",
    "openai_key",
    "elevenlabs_key",
    2000,
    "engaging,fast-paced",
    "main summarizer",
    "questioner",
    "Introduction,Content,Conclusion",
    "PODCASTFY",
    "YOUR PODCAST",
    "openai",
    0.7,
    ""
  ]
}
```

## GET /gradio_api/call/process_inputs/$EVENT_ID

### Description
Fetches the results of a podcast generation process using the provided EVENT_ID. The response will contain information about the generated podcast file, including its path and URL.

### Method
GET

### Endpoint
https://thatupiso-podcastfy-ai-demo.hf.space/gradio_api/call/process_inputs/$EVENT_ID

### Response
#### Success Response (200)
- **event** (string) - Indicates the completion status, e.g., "complete".
- **data** (array) - Contains details about the generated podcast file:
  - **path** (string) - The server path to the generated podcast file.
  - **url** (string) - The URL to access the generated podcast file (note: this URL might require prefixing with "https://thatupiso-podcastfy-ai-demo.hf.space/gradio_a/gradio_api/file=").
  - **size** (number) - The size of the podcast file (can be null).
  - **orig_name** (string) - The original name of the podcast file.
  - **mime_type** (string) - The MIME type of the file (can be null).
  - **is_stream** (boolean) - Indicates if the file is a stream.
  - **meta** (object) - Metadata about the file, including `_type`: "gradio.FileData".

### Response Example
```json
{
  "event": "complete",
  "data": [
    {
      "path": "/tmp/gradio/bcb143f492b1c9a6dbde512557541e62f090bca083356be0f82c2e12b59af100/podcast_81106b4ca62542f1b209889832a421df.mp3",
      "url": "https://thatupiso-podcastfy-ai-demo.hf.space/gradio_a/gradio_api/file=/tmp/gradio/bcb143f492b1c9a6dbde512557541e62f090bca083356be0f82c2e12b59af100/podcast_81106b4ca62542f1b209889832a421df.mp3",
      "size": null,
      "orig_name": "podcast_81106b4ca62542f1b209889832a421df.mp3",
      "mime_type": null,
      "is_stream": false,
      "meta": {
        "_type": "gradio.FileData"
      }
    }
  ]
}
```
```

--------------------------------

### Set User Instructions in YAML Configuration

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/how-to.md

Use this YAML snippet to define specific instructions for the AI hosts, guiding the conversation's focus.

```yaml
user_instructions: "Make connections with quantum computing"
```

--------------------------------

### Common Docker Commands for Podcastfy

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

A collection of common Docker commands for managing Podcastfy containers, including pulling images, starting services, building, viewing logs, and stopping containers.

```bash
# Pull latest production image
docker pull ghcr.io/souzatharsis/podcastfy:latest

# Pull development image
docker pull ghcr.io/souzatharsis/podcastfy:dev

# Start production service
docker-compose up podcastfy

# Start development environment
docker-compose up podcastfy-dev

# Run tests
docker-compose up test

# Build images locally
docker-compose build

# View logs
docker-compose logs

# Stop all containers
docker-compose down
```

--------------------------------

### Select Google Gemini Multi-speaker TTS Model

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

Demonstrates how to select a specific Text-to-Speech model for podcast generation. This example uses Google's recommended multispeaker model.

```python
audio_file = generate_podcast(urls=["https://en.wikipedia.org/wiki/Podcast"], tts_model="geminimulti")
```

--------------------------------

### Initiate Podcast Processing via cURL

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/api.md

Send a POST request to the Podcastfy API to start podcast generation. This request returns an EVENT_ID required for fetching the results.

```bash
curl -X POST https://thatupiso-podcastfy-ai-demo.hf.space/gradio_api/call/process_inputs \
  -H "Content-Type: application/json" \
  -d '{
    "data": [
      "text_input",
      "https://yourwebsite.com",
      [],  # pdf_files
      [],  # image_files
      "gemini_key",
      "openai_key",
      "elevenlabs_key",
      2000,  # word_count
      "engaging,fast-paced",  # conversation_style
      "main summarizer",  # roles_person1
      "questioner",  # roles_person2
      "Introduction,Content,Conclusion",  # dialogue_structure
      "PODCASTFY",  # podcast_name
      "YOUR PODCAST",  # podcast_tagline
      "openai",  # tts_model
      0.7,  # creativity_level
      ""  # user_instructions
    ]
  }'
```

--------------------------------

### Initialize Google Generative AI

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

Initializes the Google Generative AI client using an API key loaded from environment variables. This setup is required for utilizing Google's LLM models through the podcastfy package.

```python
import os
import google.generativeai as genai
from dotenv import load_dotenv
from podcastfy.client import generate_podcast  

load_dotenv()
```

--------------------------------

### Create Directory and Navigate

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

Create a new directory for Podcastfy and navigate into it.

```bash
mkdir -p /path/to/podcastfy
cd /path/to/podcastfy
```

--------------------------------

### Podcastfy CLI Help

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/cli.md

Display all available command-line options and their descriptions for the Podcastfy client.

```bash
python -m podcastfy.client --help
```

--------------------------------

### Configure Technical Tutorial Podcast

Source: https://github.com/souzatharsis/podcastfy/blob/main/paper/paper.md

Sets up configuration for generating a technical tutorial podcast with specific dialogue structure and engagement techniques.

```python
tutorial_config = {
    "word_count": 2500,
    "conversation_style": ["instructional", "step-by-step"],
    "roles_person1": "expert developer",
    "roles_person2": "learning developer",
    "dialogue_structure": [
        "Concept Introduction",
        "Technical Background",
        "Implementation Steps",
        "Common Pitfalls",
        "Best Practices"
    ],
    "engagement_techniques": [
        "code examples",
        "real-world applications",
        "troubleshooting tips"
    ],
    "creativity": 0.4
}

generate_podcast(
    urls=["https://tech-blog.com/tutorial"],
    conversation_config=tutorial_config
)
```

--------------------------------

### Configure Daily News Briefing Podcast

Source: https://github.com/souzatharsis/podcastfy/blob/main/paper/paper.md

Sets up configuration for a concise and informative daily news briefing podcast, including market updates and weather.

```python
news_config = {
    "word_count": 1500,
    "conversation_style": ["concise", "informative"],
    "podcast_name": "Morning Briefing",
    "dialogue_structure": [
        "Headlines",
        "Key Stories",
        "Market Update",
        "Weather"
    ],
    "roles_person1": "news anchor",
    "roles_person2": "field reporter",
    "creativity": 0.3
}

generate_podcast(
    urls=[
        "https://news-source.com/headlines",
        "https://market-updates.com/today"
    ],
    conversation_config=news_config
)
```

--------------------------------

### Run Podcastfy CLI with Custom Configuration

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/how-to.md

Execute the Podcastfy client from the command line, specifying a URL and a path to your custom configuration file.

```bash
python -m podcastfy.client --url https://en.wikipedia.org/wiki/Artificial_intelligence --conversation-config path/to/custom_config.yaml
```

--------------------------------

### Configure podcast generation with Japanese art images

Source: https://github.com/souzatharsis/podcastfy/blob/main/usage/examples.ipynb

Sets up the conversation configuration and image paths for generating a podcast discussing Japanese art. Includes user instructions for overlapping sentences and personal connections.

```python
images = ["https://raw.githubusercontent.com/souzatharsis/podcastfy/refs/heads/main/data/images/japan_1.jpg",
          "https://raw.githubusercontent.com/souzatharsis/podcastfy/refs/heads/main/data/images/japan2.jpg"]
```

```python
conversation_config = {
    "roles_person1": "Abstract Art Ph.D.",
    "roles_person2": "Creative Abstract Artist",
    "podcast_name": "Japan Arts Podcast",
    "podcast_tagline": "Because Art is Everywhere",
    "creativity": 1,
    "user_instructions": "Speakers should often overlap in their sentences. The conversation should be about the relationship between art and life. Person2 should make connections with her own life!"
}
```

--------------------------------

### Configure podcast generation with abstract art images

Source: https://github.com/souzatharsis/podcastfy/blob/main/usage/examples.ipynb

Sets up the conversation configuration and image paths for generating a podcast discussing abstract art. The configuration specifies roles, podcast details, and creativity level.

```python
conversation_config = {
    "roles_person1": "Abstract Art Ph.D. Professor",
    "roles_person2": "Abstract Art Grad Student",
    "podcast_name": "Artfy Podcast",
    "podcast_tagline": "Because Art is Everywhere",
    "creativity": 1
}
```

```python
images = ["https://raw.githubusercontent.com/souzatharsis/podcastfy/refs/heads/main/data/images/Senecio.jpeg",
          "https://raw.githubusercontent.com/souzatharsis/podcastfy/refs/heads/main/data/images/connection.jpg"]
```

--------------------------------

### Create New Branch

Source: https://github.com/souzatharsis/podcastfy/blob/main/GUIDELINES.md

Create a new branch for your feature or bug fix before starting development.

```bash
git checkout -b feature/your-feature-name
```

--------------------------------

### Generate Podcast from Image Files

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/cli.md

Create a podcast by providing image files. The content will be extracted from the images.

```bash
python -m podcastfy.client --image path/to/image1.jpg --image path/to/image2.png
```

--------------------------------

### Generate Podcast from Wikipedia URL

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

Initiates podcast generation from a single URL. This example uses a Wikipedia page as input.

```python
audio_file = generate_podcast(urls=["https://en.wikipedia.org/wiki/Podcast"])
```

--------------------------------

### Generate Documentation

Source: https://github.com/souzatharsis/podcastfy/blob/main/GUIDELINES.md

Generate the project documentation using Sphinx.

```bash
make doc-gen
```

--------------------------------

### Generate Podcast from File of URLs

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/cli.md

Create a podcast by providing a text file containing a list of URLs.

```bash
python -m podcastfy.client --file path/to/urls.txt
```

--------------------------------

### Embed generated podcast audio from PDF (commented out)

Source: https://github.com/souzatharsis/podcastfy/blob/main/usage/examples.ipynb

A commented-out example showing how to embed the audio generated from a PDF. This snippet is not active.

```python
#embed_audio(audio_file)
```

--------------------------------

### Generate Conversational Content

Source: https://github.com/souzatharsis/podcastfy/blob/main/paper/paper.md

Example of generating conversational text using a provided input. This snippet assumes a 'generator' object is already initialized.

```python
input_text = "This is a sample input text about artificial intelligence."
generated_conversation = generator.generate_conversation(input_text)

print("Generated Conversation:")
print(generated_conversation)
```

--------------------------------

### Initialize Content Generator

Source: https://github.com/souzatharsis/podcastfy/blob/main/paper/paper.md

Shows how to initialize the ContentGenerator module, requiring an API key for its operation.

```python
from podcastfy.content_generator import ContentGenerator

# Initialize the content generator
generator = ContentGenerator(api_key="<GEMINI_API_KEY>")
```

--------------------------------

### Select Microsoft Edge TTS Model

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

Demonstrates how to select a specific Text-to-Speech model for podcast generation. This example uses the Microsoft Edge model.

```python
audio_file = generate_podcast(urls=["https://en.wikipedia.org/wiki/Podcast"], tts_model="edge")
```

--------------------------------

### Generate Podcast using Python

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/index.md

Use the `generate_podcast` function from the `podcastfy.client` module to create a podcast from a list of URLs. Ensure you have the necessary imports.

```python
from podcastfy.client import generate_podcast

audio_file = generate_podcast(urls=["<url1>", "<url2>"])
```

--------------------------------

### Truncated Error Message for API Key

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

Displays a truncated error message indicating a missing API key or ADC, guiding the user on how to resolve the issue.

```text
Error (truncated):
 [31mDefaultCredentialsError [39m: 
  No API_KEY or ADC found. Please either:
    - Set the `GOOGLE_API_KEY` environment variable.
    - Manually pass the key with `genai.configure(api_key=my_api_key)`.
    - Or set up Application Default Credentials, see https://ai.google.dev/gemini-api/docs/oauth for more information.
```

--------------------------------

### Select Google Gemini TTS Model

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

Demonstrates how to select a specific Text-to-Speech model for podcast generation. This example uses Google's single speaker Journey model.

```python
audio_file = generate_podcast(urls=["https://en.wikipedia.org/wiki/Podcast"], tts_model="gemini")
```

--------------------------------

### Configure Language Learning Podcast

Source: https://github.com/souzatharsis/podcastfy/blob/main/paper/paper.md

Configures Podcastfy to generate educational language learning content with vocabulary explanations and cultural context.

```python
language_config = {
    "output_language": "Spanish",
    "word_count": 1000,
    "conversation_style": ["educational", "casual"],
    "engagement_techniques": [
        "vocabulary explanations",
        "cultural context",
        "pronunciation tips"
    ],
    "roles_person1": "language teacher",
    "roles_person2": "curious student",
    "creativity": 0.6
}

generate_podcast(
    urls=["https://spanish-content.com/article"],
    conversation_config=language_config
)
```

--------------------------------

### Generate Podcast from URLs and File

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/cli.md

Combine URLs and a file containing URLs to generate a single podcast.

```bash
python -m podcastfy.client --url https://example.com/article1 --file path/to/urls.txt
```

--------------------------------

### Initialize Gradio Client in Python

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/api.md

Instantiate the Gradio client to connect to the specified API endpoint.

```python
from gradio_client import Client, handle_file

client = Client("thatupiso/Podcastfy.ai_demo")
```

--------------------------------

### Academic Debate Conversation Configuration

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/conversation_custom.md

Configure podcast settings for a formal academic debate. This setup increases word count, uses analytical conversation styles, defines specific roles for debaters, structures the dialogue like a debate, and employs critical engagement techniques. Set creativity to a low value for factual accuracy.

```python
{
    "word_count": 3000,  # Longer to allow for detailed arguments
    "conversation_style": ["formal", "analytical", "critical"],  # Appropriate for academic discourse
    "roles_person1": "thesis presenter",  # Presents the main argument
    "roles_person2": "counterargument provider",  # Challenges the thesis
    "dialogue_structure": [
        "Opening Statements",
        "Thesis Presentation",
        "Counterarguments",
        "Rebuttals",
        "Closing Remarks"
    ],  # Mimics a structured debate format
    "podcast_name": "Scholarly Showdown",
    "podcast_tagline": "Where Ideas Clash and Knowledge Emerges",
    "engagement_techniques": [
        "socratic questioning",
        "historical references",
        "thought experiments"
    ],  # Techniques to stimulate critical thinking
    "creativity": 0  # Low creativity to maintain focus on facts and logic
}
```

--------------------------------

### Generate Podcast from File Path

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

Generates a podcast using a list of URLs provided in a text file. Each URL should be on a new line.

```python
audio_file = generate_podcast(file_path="./data/urls.txt")
```

--------------------------------

### Generate Podcast from URLs and Images

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/cli.md

Generate a podcast by combining content from both web URLs and image files.

```bash
python -m podcastfy.client --url https://example.com/article1 --image path/to/image1.jpg
```

--------------------------------

### Using OpenAI GPT-4 Turbo with Podcastfy

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/how-to.md

Select a specific cloud-based LLM model like OpenAI's GPT-4 Turbo by providing the model name and API key label to the generate_podcast function. Ensure your environment variables are correctly set.

```python
audio_file = generate_podcast(
    urls=["https://en.wikipedia.org/wiki/Artificial_intelligence"],
    llm_model_name="gpt-4-turbo",
    api_key_label="OPENAI_API_KEY"
)
```

--------------------------------

### Import necessary libraries

Source: https://github.com/souzatharsis/podcastfy/blob/main/usage/examples.ipynb

Imports the generate_podcast function from the podcastfy client.

```python
from podcastfy.client import generate_podcast
```

--------------------------------

### Import Podcastfy and Load Environment Variables

Source: https://github.com/souzatharsis/podcastfy/blob/main/podcastfy.ipynb

Imports the necessary `generate_podcast` function from the podcastfy client and loads environment variables using `dotenv`. This is a prerequisite for using most podcastfy functionalities.

```python
from podcastfy.client import generate_podcast
# !pip install  duckduckgo-search

import os
from dotenv import load_dotenv

# This automatically loads from .env file

load_dotenv()
```

--------------------------------

### Check Production Version

Source: https://github.com/souzatharsis/podcastfy/blob/main/docs/source/usage/docker.md

Run a command to check the production version of the Podcastfy Docker image.

```bash
docker run --rm ghcr.io/souzatharsis/podcastfy:latest python3 -c "import podcastfy"
```