Podcastfy

Transform any content into engaging AI-generated podcasts using TensorX models.

What is Podcastfy?

Podcastfy is an open-source Python package that transforms multi-modal content (text, images, websites, PDFs, YouTube videos) into engaging, multi-lingual audio conversations. It's an open-source alternative to NotebookLM's podcast feature.

Why Podcastfy + TensorX?

🎧 Multi-modal input - Websites, PDFs, images, YouTube videos, and more
🌍 Multilingual - Generate podcasts in multiple languages
⚡ Fast generation - Create 3-minute podcasts in under 20 seconds
🎨 Customizable - Control conversation style, length, and voices
📦 Python & CLI - Use as a library or command-line tool

Prerequisites

Python 3.11 or higher
ffmpeg installed (pip install ffmpeg or system package)
A TensorX API key (sign up here)

Installation

pip install podcastfy

Quick Start

Python

from podcastfy.client import generate_podcast

# Generate podcast from URLs using TensorX
audio_file = generate_podcast(
    urls=["https://en.wikipedia.org/wiki/Artificial_intelligence"],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY"
)

print(f"Podcast saved to: {audio_file}")

CLI

python -m podcastfy.client \
  --url https://en.wikipedia.org/wiki/Artificial_intelligence \
  --llm-model-name openai/deepseek/deepseek-chat-v3.1

Configuration

Environment Variables

Create a .env file in your project root:

# TensorX API Key (used for both LLM and TTS)
OPENAI_API_KEY=your-tensorx-api-key

# TensorX API Base URL
OPENAI_BASE_URL=https://api.tensorx.ai/v1

Note: The environment variable is OPENAI_BASE_URL (not OPENAI_API_BASE). This is the standard LiteLLM format.

Using TensorX for Transcript Generation

Podcastfy uses LiteLLM for LLM support. To use TensorX models:

from podcastfy.client import generate_podcast

audio_file = generate_podcast(
    urls=["https://example.com/article"],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY"
)

Model format: Use openai/ prefix followed by the TensorX model name. This tells LiteLLM to route requests to an OpenAI-compatible endpoint.

LiteLLM Model Format

Podcastfy uses LiteLLM which requires specific model naming for OpenAI-compatible APIs:

openai/<tensorx-model-name>

Examples

TensorX Model

LiteLLM Format

z-ai/glm-5.1

openai/z-ai/glm-5.1

minimax/minimax-m2.5

openai/minimax/minimax-m2.5

moonshotai/kimi-k2.5

openai/moonshotai/kimi-k2.5

deepseek/deepseek-chat-v3.1

openai/deepseek/deepseek-chat-v3.1

deepseek/deepseek-r1-0528

openai/deepseek/deepseek-r1-0528

meta-llama/llama-3.3-70b-instruct

openai/meta-llama/llama-3.3-70b-instruct

Recommended Models

Use Case

Model

Notes

General podcasts

deepseek/deepseek-chat-v3.1

Fast, great conversational quality

In-depth analysis

deepseek/deepseek-r1-0528

Better reasoning for complex topics

Technical content

z-ai/glm-5.1

Good for code and technical discussions

Vision content

moonshotai/kimi-k2.5

Image understanding

Long content

meta-llama/llama-4-maverick

Long document processing

Text-to-Speech with TensorX

Configure TensorX TTS for audio generation:

from podcastfy.client import generate_podcast

audio_file = generate_podcast(
    urls=["https://example.com/article"],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY",
    tts_model="openai"  # Uses OpenAI-compatible TTS
)

Environment Variables for TTS

# In your .env file
OPENAI_API_KEY=your-tensorx-api-key
OPENAI_BASE_URL=https://api.tensorx.ai/v1

Customization

Conversation Style

Customize the podcast conversation:

from podcastfy.client import generate_podcast

custom_config = {
    "word_count": 500,
    "conversation_style": ["casual", "informative"],
    "podcast_name": "Tech Insights",
    "creativity": 0.7,
    "output_language": "English"
}

audio_file = generate_podcast(
    urls=["https://example.com/tech-news"],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY",
    conversation_config=custom_config
)

CLI with Custom Config

Create a custom_config.yaml:

word_count: 500
conversation_style:
  - casual
  - informative
podcast_name: "Tech Insights"
creativity: 0.7
output_language: English

Run with:

python -m podcastfy.client \
  --url https://example.com/article \
  --llm-model-name openai/deepseek/deepseek-chat-v3.1 \
  --conversation-config custom_config.yaml

Generate from Multiple Sources

Multiple URLs

audio_file = generate_podcast(
    urls=[
        "https://example.com/article1",
        "https://example.com/article2",
        "https://youtube.com/watch?v=example"
    ],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY"
)

From PDF Files

audio_file = generate_podcast(
    urls=["path/to/document.pdf"],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY"
)

From Images

audio_file = generate_podcast(
    urls=["path/to/image1.jpg", "path/to/image2.png"],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY"
)

Longform Podcasts

Generate longer podcasts (20-30 minutes):

audio_file = generate_podcast(
    urls=["https://example.com/long-article"],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY",
    longform=True
)

Customize Longform Length

custom_config = {
    "max_num_chunks": 10,  # More chunks = longer podcast
    "min_chunk_size": 400  # Smaller chunks = more detail
}

audio_file = generate_podcast(
    urls=["https://example.com/article"],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY",
    longform=True,
    conversation_config=custom_config
)

Transcript Only

Generate just the transcript without audio:

from podcastfy.client import generate_podcast

transcript = generate_podcast(
    urls=["https://example.com/article"],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY",
    transcript_only=True
)

print(transcript)

CLI

python -m podcastfy.client \
  --url https://example.com/article \
  --llm-model-name openai/deepseek/deepseek-chat-v3.1 \
  --transcript-only

Multilingual Podcasts

Generate podcasts in different languages:

custom_config = {
    "output_language": "French"
}

audio_file = generate_podcast(
    urls=["https://example.com/article"],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY",
    conversation_config=custom_config
)

Supported languages depend on the TTS model capabilities.

Troubleshooting

API Key Errors

Verify your .env file contains:

OPENAI_API_KEY=your-tensorx-api-key
OPENAI_API_BASE=https://api.tensorx.ai/v1

Test your API key:

curl https://api.tensorx.ai/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Model Not Found

Ensure you're using the correct LiteLLM format:

✅ openai/deepseek/deepseek-chat-v3.1
❌ deepseek/deepseek-chat-v3.1

Audio Generation Fails

Ensure ffmpeg is installed: ffmpeg -version
Check TTS configuration in your environment
Verify API key has sufficient credits

Content Extraction Fails

Check the URL is accessible
For PDFs, ensure the file path is correct
For YouTube, verify the video is public

Complete Example

import os
from podcastfy.client import generate_podcast

# Set environment variables
os.environ["OPENAI_API_KEY"] = "your-tensorx-api-key"
os.environ["OPENAI_BASE_URL"] = "https://api.tensorx.ai/v1"

# Custom configuration
config = {
    "word_count": 800,
    "conversation_style": ["engaging", "educational"],
    "podcast_name": "AI Weekly",
    "creativity": 0.8
}

# Generate podcast
audio_file = generate_podcast(
    urls=[
        "https://en.wikipedia.org/wiki/Large_language_model",
        "https://en.wikipedia.org/wiki/Transformer_(deep_learning_architecture)"
    ],
    llm_model_name="openai/deepseek/deepseek-chat-v3.1",
    api_key_label="OPENAI_API_KEY",
    conversation_config=config
)

print(f"🎙️ Podcast generated: {audio_file}")

Good afternoon