The full gallery
Tech stack
60 projects
Master vocabulary with AI-powered translations, visual mnemonics, and pronunciation guides.
LandoLorinse · HN
Vocab Top – AI-powered vocabulary builder that helps you retain words
LingoRise
@DavidMaesela · X
Excited to share the new app I created with @Jotform! Check it out:
Rewrite AI-generated text to sound human while preserving meaning.
WriteHybrid — 可绕过所有顶级 AI 检测器的 AI 人性化工具
API providing token-level citations for LLM output grounded in attention analysis.
apoorvumang · HN
TokenPath – token-level citations for LLM output, read from attention
Speak or type a rough thought and HUMM turns it into a message worth sending. 30+ tones, 16 languages, a private journal and a browser extension.
@Raj_kabadi · X
Check out what I just built with @Lovable ! Here u need to speak and all ur words will be transcribed and u can choose any required tone In both the application it's similar but the features are different
AI-powered e-book reader that integrates notes, reading, and AI responses to build and systematize your personal knowledge base.
mekery · V2EX
我开源了一个 AI 电子书阅读器，欢迎大家体验 Hi V 友们, AI 时代，搭建自己的知识库非常有必要，我想把笔记、阅读和 AI 回答集成在一起，不断完善知识的积累和系统化，因此做了这款阅读器。 ## 整体预览  ## 阅读 ### 书架  ### 阅读视图   ### 目录、书签、高亮、注释和 AI  ###
Self-hosted language reader with reading exercises, cloze practice, and spaced repetition study.
3stacks · HN
Lector, a FOSS self-hosted language reader (with a cloud option)
Transform AI-generated text into natural-sounding human writing.
Humanizadordeia.app — 将AI文本转化为自然人类写作。1）人性化处理，让 AI 文本更自然、更贴近人工写作与品牌口吻；2）检测服务，帮助识别潜在 AI 生成内容，提升合规与质量。支持多语种、极速处理、保留语义与风格。免注册体验 300 字，适合博主、营销团队、跨境站点、教育与企业内容运营。以先进模型（GPT、Claude、Gemini 等）驱动。
Size your way to private local AI. Directional sizing for one resident text model: KV memory, combined prefill/decode serving, and runtime sessions. Compare eligible on-prem, sover
juxhinr · GitHub
bindwidth Evidence-aware on-prem LLM inference sizing and TCO calculator
Echo – Fable-level results at 1/3 the cost using open-weight models
adam_rida · HN
Echo – Fable-level results at 1/3 the cost using open-weight models
Transcribe and summarize YouTube videos, podcasts, PDFs, and MP3/MP4 files with AI.
sipsip.ai — 支持30+平台视频AI转录并提取摘要，订阅RSS可以每天发送早报
Speech to text dictation and multi-engine speed benchmarking. Compare OpenAI GPT-Transcribe, Deepgram Nova-3, NVIDIA Parakeet, and Fish Audio with local IndexedDB privacy.
@alvaisy · X
finished voice to text small web app for my own itch. it's opensource. use openrotuer key. and use it with 4 models.
