Podcastfy
Configure Podcastfy to generate podcasts through TensorX.
What is Podcastfy?
Podcastfy is an open-source Python package that converts text, images, websites, PDFs and video sources into multi-speaker audio.
Prerequisites
Python 3.11 or higher
ffmpeg installed (
pip install ffmpegor system package)A TensorX API key (sign up here)
Installation
pip install podcastfyQuick Start
Python
CLI
Configuration
Environment Variables
Create a .env file in your project root:
Using TensorX for Transcript Generation
Podcastfy uses LiteLLM for LLM support. To use TensorX models:
LiteLLM Model Format
Podcastfy uses LiteLLM which requires specific model naming for OpenAI-compatible APIs:
Replace <tensorx-model-name> with an ID returned by GET /v1/models.
Model selection
Call GET /v1/models with your TensorX API key and use one of the returned IDs. If the integration depends on a capability or token limit, query GET /v1/model/info before selecting the model. See Models for examples.
Text-to-Speech with TensorX
Configure TensorX TTS for audio generation:
Environment Variables for TTS
Customization
Conversation Style
Customize the podcast conversation:
CLI with Custom Config
Create a custom_config.yaml:
Run with:
Generate from Multiple Sources
Multiple URLs
From PDF Files
From Images
Longform Podcasts
Generate longer podcasts (20-30 minutes):
Customize Longform Length
Transcript Only
Generate just the transcript without audio:
CLI
Multilingual Podcasts
Generate podcasts in different languages:
Supported languages depend on the TTS model capabilities.
Troubleshooting
API Key Errors
Verify your
.envfile contains:Test your API key:
Model Not Found
Ensure you're using the correct LiteLLM format:
openai/z-ai/glm-5.2z-ai/glm-5.2
Audio Generation Fails
Ensure ffmpeg is installed:
ffmpeg -versionCheck 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
Resources
See Also
Audio API - TensorX text-to-speech and speech-to-text
API Examples - Code examples for TensorX API
SurfSense - Another tool with podcast generation
Open Notebook - NotebookLM alternative with podcasts
Last updated
Was this helpful?

