Tag
#Local AI
10 posts and news items use this tag.
Marker Hands-on: Is It Easier Than MinerU for PDF-to-Markdown?
I tested Marker’s fast mode on an Apple Silicon Mac. It is already useful for ordinary text-based PDFs, but equations and tables can still fail. I also explain where it fits next to MinerU.
Meetily Hands-On: A Local AI Tool for Meeting Transcription, Transcripts, and Traditional Chinese Summaries
Meetily is an open-source, privacy-first AI meeting assistant that can record, transcribe, and generate summaries locally. I tested v0.4.0 and organized the installation flow, Chinese transcription model setup, Traditional Chinese summaries, and the situations where it makes sense to use.
Upscayl Hands-On: A Free, Open-Source Local AI Image Upscaler
I tested Upscayl, a free and open-source AI image upscaling tool, from installing it through GitHub Releases and Homebrew, choosing the language on first launch, selecting a model, and using the Digital Art model to upscale a He-Man image by 4x.
SmartSub 妙幕 Hands-on: The Least Fussy Local Video Subtitle Translation Tool I’ve Used So Far
SmartSub 妙幕 is a local-first desktop subtitle tool that can transcribe videos, translate subtitles, create bilingual subtitles, and burn subtitles into video. This article records my tests with DeepSeek translation, faster-whisper, CUDA acceleration, and how it differs from VideoLingo.
Hands-on with Handy Offline Voice Input: Paired with Breeze ASR 25, a Chinese-English Mixed Input Setup Built for Taiwanese Users
Handy is a free, open-source desktop voice input tool that runs fully offline. In this article, I test installation and configuration on macOS/Windows/Linux, paired with the Breeze ASR 25 model optimized for everyday Chinese-English mixed speech in Taiwan, to build a privacy-focused voice input experience.
LLM Wiki Hands-on: Building a Personal Offline Knowledge Base That Large Models Can Organize and Update Automatically
Do your notes always feel tedious to organize? LLM Wiki is a personal knowledge base tool built around ideas from Andrej Karpathy. It can automatically read documents, run a two-stage chain-of-thought analysis, generate interconnected Wiki pages, and work well with Obsidian and local AI models.
Vibe Review: A Cross-Platform Offline AI Speech-to-Text Tool for Beginners — Clean, Intuitive, One-Click
Dread the Whisper command line or find other tools too complicated to set up? Vibe is a minimal, hassle-free offline speech-to-subtitle tool. The feature set is simple, but the interface is clean and easy to pick up — a solid choice for less technical users.
MinerU Hands-on: Open-Source PDF and Multi-Format Document Parsing on macOS/Windows/Linux
When dealing with complex layouts, scanned documents, or formulas, traditional PDF-to-text tools often fall short. The open-source framework MinerU combines layout analysis with vision-language models (VLM) to convert PDFs, images, and Office files into accurate Markdown, tables, and LaTeX formulas in one step. This article tests both the online Web version and local CLI/API deployment workflow.
Removerized: An Offline Browser-Based AI Background Removal and Image Enhancement Tool
Removerized lets you handle background removal, upscaling, and batch processing directly in the browser, without uploading data to the cloud, balancing speed and privacy.
Installing and Testing Modly, a Local AI Image-to-3D Mesh Generation Tool
Want to quickly turn 2D images into high-detail 3D models without paying or uploading private work to the cloud? Modly lets you run AI 3D generation directly on your local GPU.