souzatharsis/podcastfy
Podcastfy
Podcastfy is an AI content-to-podcast generator that converts text, URLs, PDFs, images, and videos into conversational audio podcasts. It integrates with over 100 language models for transcript creation and multiple text-to-speech engines for audio output, with support for customizable dialogue style and optional local transcript generation for privacy.
The project distinguishes itself through a flexible architecture that decouples job submission from result retrieval via asynchronous polling, normalizes heterogeneous inputs into uniform text, and routes content through pluggable LLM and TTS backends with template-driven dialogue assembly. Users can customize conversation tone, speaker roles, dialogue structure, and creativity level through configuration files, and can run transcript generation locally using a local language model for greater privacy and offline use.
Beyond core podcast generation, the system supports content extraction from websites, videos, images, and documents, multilingual audio generation, Q&A content generation from text, and topic-based podcast creation through real-time web search. It also offers transcript-only generation and the ability to produce audio from pre-written transcripts.
Features
- Podcast Generators - Transforms text, URLs, PDFs, or images into spoken audio conversations using generative AI.
- Content-to-Podcast Converters - Turns articles, documents, images, and web pages into spoken audio conversations using generative AI.
- AI Model Integrations - Integrates with over 100 language models for transcript generation through a unified interface.
- Local LLM Transcript Generators - Creates conversation transcripts on the user's own machine using a local language model for privacy and control.
- LLM-Agnostic Generators - Generates conversation transcripts by routing prompts to any of over 100 language models through a unified interface, supporting both cloud and local inference.
- Text-to-Speech - Synthesizes cleaned text into audio files using third-party text-to-speech services.
- Multi-Modal Audio Conversation Generators - Transforms text, images, websites, PDFs, and videos into multilingual audio conversations using generative AI.
- Text To Speech - Converts cleaned text into audio files using third-party text-to-speech services.
- AI Content-to-Podcast Generators - Converts text, URLs, PDFs, and images into conversational audio podcasts using generative AI and text-to-speech.
- Multi-LLM Podcast Engines - Integrates with over 100 language models for transcript creation and multiple TTS engines for audio output.
- Pluggable TTS Backends - Converts transcript text into audio by selecting among multiple third-party TTS engines through a common abstraction layer.
- Content-to-Podcast Converters - Converts web article URLs into spoken audio conversations using text-to-speech models.
- Conversation Style Configurations - Adjusts the tone, structure, and format of generated conversations using user-defined configuration files.
- Local Model Execution - Runs transcript generation on the user's own machine using a local language model for privacy.
- Multimodal Data Extractors - Pulls text from websites, videos, images, and documents to feed into podcast generation pipelines.
- Customizable Dialogue Synthesizers - Adjusts conversation tone, speaker roles, structure, and creativity level to produce tailored podcast episodes.
- Multi-Speaker Dialogue Templates - Constructs multi-speaker conversation scripts using user-defined configuration files for tone, structure, and roles.
- Podcast Style Customizers - Adjusts conversation tone, speaker roles, dialogue structure, and creativity level for generated audio.
- Topic-Based Podcast Creators - Generates podcast episodes from user-provided topics by performing real-time web searches for content.
- Multilingual Audio Generators - Produces spoken audio content in multiple languages from text, images, or URLs.
- Transcript-to-Audio Renderers - Accepts a pre-written transcript file and renders it as an audio conversation.
- Podcast Transcript and Audio Customizers - Adjusts conversation style, language, structure, and voices to tailor generated podcasts.
- Content Extraction - Pulls text content from websites, videos, and documents by delegating to specialized extractors for each source type.
- Multi-Format Content Extractors - Pulls text from websites, PDFs, images, and videos using specialized extractors for each source type.
- Multi-Modal Content Normalizers - Transforms heterogeneous inputs like text, URLs, images, and PDFs into a uniform text representation.
- Text-to-Speech Engines - Chooses between different text-to-speech services to produce the final audio output.
- Local Language Model Hosting - Generates conversation transcripts using a language model hosted on your own computer instead of a cloud service.
- Voice & Multimodal Assistants - Python tool for transforming content into multilingual audio conversations.
- Media and Communication - Converts multi-modal content into podcast-style dialogues.
- General Programming Resources - Converts text content into podcast-style audio.
