Cloudflare's recent voice agents release provides a free daily tier for Deepgram STT, TTS use. So I created a Voice AI Agent pipeline that runs on Cloudflare workers with Durable Objects and it interfaces with an Arduino ESP32. This lets you bring any LLM to power your Voice AI Toys and Desk companions with STT + TTS handled natively. Comments URL: https://news.ycombinator.com/item?id=47810376 Points: 2 # Comments: 0
Hi there. I was looking for a pastebin-like instant solution for online meetings — a shared whiteboard with real-time sync. Of course there are Excalidraw and tldraw, BUT they require signup and are overgrown with features I don't need. So I just built cnvs.app — instant sharing, no signup, real-time sync with all the essentials: drawing, writing, and pasting images. All in one day. On day two I added sticky notes, full mobile support, and Mermaid diagrams (cool thing — try pasting some Mermaid syntax there!) and deployed to Cloudflare so everyone can use it for free. Be creative. Have fun :) Comments URL: https://news.ycombinator.com/item?id=47763731 Points: 1 # Comments: 0
AI 早报 2026-02-24 视频版：YouTube ｜ 哔哩哔哩 概览 模型发布 OpenAI 在 Realtime API 中上线 gpt-realtime-1.5 语音模型 ↗ #1 Guide Labs 推出可解释因果扩散语言模型 Steerling-8B ↗ #2 开发生态 OpenAI Responses API 新增 WebSocket 模式 ↗ #3 Google 回应封禁滥用 Antigravity 的 Gemini 订阅用户 ↗ #4 Anthropic 推广 COBOL 代码自动化迁移方案 ↗ #5 产品应用 Gemini 上线视频模板功能 ↗ #6 openclaw 发布 2026.2.22 版本 ↗ #7 行业动态 Anthropic 指控三家中国 AI 实验室进行工业级模型蒸馏…