How to Turn Any Book into a Multi-Voice Audio Production with Alexandria
Alexandria transforms any text into a multi-voice audio production using LLM analysis and neural speech synthesis. Here's how it works and whether it's worth trying.
Language
HomeLanguages
Sections
Machine learning frameworks, data tooling, and the libraries powering modern AI applications.
Alexandria transforms any text into a multi-voice audio production using LLM analysis and neural speech synthesis. Here's how it works and whether it's worth trying.
DebugSwift turns your iOS app into a full debugging lab with network inspection, view hierarchy, memory leak detection, and more — right on device.
MLX-Audio brings lightning-fast TTS, STT, and STS capabilities to Apple Silicon Macs. Built on Apple's MLX framework, it offers Whisper, Kokoro, voice cloning, and more—all running locally without cloud costs.
AI Data Science Team by Business Science automates routine Data Science tasks with specialized AI agents and a visual pipeline builder.
org-ai is an Emacs extension that integrates AI models directly into your workflow, enabling code generation, image creation, voice input, and project analysis without leaving your editor.
Awesome ChatGPT is a curated collection of 150+ tools and extensions that supercharge your AI workflow. A must-have for developers.
Keras 3 unifies TensorFlow, PyTorch, and JAX in one framework. Get up to 350% performance boost by switching backends with a single line of code.
CLIP from OpenAI learns visual concepts from natural language descriptions, enabling zero-shot classification without labeled datasets.
Meta's Habitat-Sim delivers thousands of FPS for training home robots, eliminating expensive real-world testing.
Neural Photo Editor lets you paint on photos while neural networks generate realistic continuations. Great for designers, researchers, and GAN enthusiasts.
Paperless-ai is an intelligent extension for Paperless-ngx that uses AI to automatically classify documents, enable natural language search, and handle metadata.
Agent Squad by AWS Labs lets you build multi-agent AI systems where specialized agents work together seamlessly, with intelligent routing and context management.
GitHubDaily is a curated collection of the best open-source projects, manually selected by enthusiasts to save developers time and help them discover quality tools.
PageLM is an open-source alternative to NotebookLM that transforms textbooks into AI podcasts, quizzes, flashcards, and interactive study tools.
Discover how to add professional beauty filters to your app in hours using GPUPixel, a cross-platform C++ library with real-time video processing capabilities.
Vibe is a desktop app for transcribing audio and video offline, built on OpenAI Whisper. Offers privacy, 100+ languages, batch processing, and GPU acceleration.
Scriberr is an open-source, fully offline audio and video transcription app that prioritizes privacy—no subscriptions, no cloud uploads, just local processing with LLM integration.
Skip the monthly fees for Suno or Udio. ACE-Step UI brings full-featured AI music generation to your own GPU — free, private, and surprisingly polished.
Marimo is a reactive Python notebook that solves Jupyter's hidden state and versioning problems. It saves notebooks as .py files, making them Git-friendly.
MusicGPT transforms text prompts into music compositions. An open-source tool for game developers, video bloggers, and musicians seeking quick audio generation.
AIdea is an open-source Flutter app combining AI chatbots, image generation, and Chinese language models — all in one cross-platform solution with 6.8k GitHub stars.
MCP bridges AI assistants like Claude with Figma, letting neural networks read designs, export tokens, and even generate layouts from text descriptions.