1
Show HN: Dictata – Local Whisper dictation with LLM cleanup
本地语音转文字加AI润色，隐私安全还免费
Article URL: https://github.com/AntoineChatry/Dictata Comments URL: https://news.ycombinator.com/item?id=49306462 Points: 3 # Comments: 0
2
Show HN: WhisperKeys - Offline macOS dictation, key-by-key
本地离线听写，WhisperKeys让你的Mac上所有应用都能通过语音输入，隐私无忧。
Article URL: https://github.com/j-sofia/WhisperKeys Comments URL: https://news.ycombinator.com/item?id=49130297 Points: 2 # Comments: 1
3
Open Source, Free Tier Capable Whispr Using Cloudflare AI
开源语音转文字桌面应用，基于Whisper和Cloudflare AI，实现实时转录与智能格式化
Article URL: https://github.com/PrestigePvP/Voicebox Comments URL: https://news.ycombinator.com/item?id=48929870 Points: 6 # Comments: 2
4
AI 转录 Mac 工具 MacWhisper 14 发布：新增编辑器视图，修复 CPU 占用过高问题
MacWhisper 14 更新带来编辑器视图，大幅提升转录编辑效率，同时修复 CPU 过高问题。
IT之家 7 月 15 日消息，开发者乔迪 · 布鲁因（Jordi Bruin）昨日（7 月 14 日）发布博文，宣布推出 MacWhisper 14.0 更新， 重点提升转录性能并新增编辑器视图。 IT之家注：MacWhisper 于 2023 年推出，是一款适用于 Mac 设备的 AI 驱动转录…
5
I built a WhatsApp-to-book pipeline with Make.com, OpenAI and Lulu.com — here's the full stack
无需安装应用，用WhatsApp语音给祖父母出书，这套全栈自动化方案太暖心了
Minha Historia turns your parents' voice notes into a hardcover memoir book. The French version is Mon Livre de Vie . Here's how the entire pipeline w…
6
Listening Between the Lines: Joint Learning of ASR Embeddings and LLM-Augmented Linguistics for Dementia Detection
将Whisper的ASR嵌入与LLM语言学结合，开创非侵入式痴呆症早期筛查新路径。
arXiv:2606.30675v1 Announce Type: cross Abstract: Early detection of dementia through speech analysis offers a non-invasive screening alternative, but…
7
I rebuilt Siri AI from scratch and open sourced it
开源了完全可配置的Siri AI，本地运行保障隐私，无数据外泄，支持唤醒词、转录引擎、主题、技能全定制。
Article URL: https://github.com/wassgha/opendex Comments URL: https://news.ycombinator.com/item?id=48715439 Points: 1 # Comments: 1
8
Show HN: AI-whisper – Claude works better when Codex watches its back
让Claude与Codex协作的开源AI工具，支持暂停恢复，将模糊想法转化为可执行计划。
Article URL: https://ai-creed.dev/projects/ai-whisper/ Comments URL: https://news.ycombinator.com/item?id=48698924 Points: 3 # Comments: 2
9
Building a Voice AI Platform with 28 Modules in Python
开源语音AI平台Omni-VRAM集成了28个Python模块，支持语音识别、实时流、情绪识别等，<200ms延迟，免费可用！
What I Built Omni-VRAM is an open-source voice AI platform with 28 modules. GitHub: https://github.com/Liangchenxu/Omni-VRAM Features Speech Recogniti…
10
Whisper-GPT -- Continuous Discrete Hybrid Representation Language Models For Speech And Music
一种新颖的连续离散混合表示语言模型，同时处理语音与音乐，统一建模音频生成和理解。
arXiv:2412.11449v2 Announce Type: replace-cross Abstract: We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that al…
11
You can't whisper at an AI agent
与AI agent对话，清晰指令比窃窃私语更有效。这篇来自Stripe团队的实践洞察，揭示了代理交互中指令粒度与系统响应的微妙关系——你的"呢喃"可能被当作噪声，而明确意图才是驱动智能的关键。
Article URL: https://stripe.dev/blog/ai-steering-experiments Comments URL: https://news.ycombinator.com/item?id=48162696 Points: 1 # Comments: 1
12
Show HN: Whisper Large V3 Turbo Stream API
快速、廉价的语音转文字API，基于Whisper Large V3 Turbo，成本比主流服务低5-10倍，早鸟体验中。
Article URL: https://www.makeform.ai/f/mtwDANdO Comments URL: https://news.ycombinator.com/item?id=48169294 Points: 1 # Comments: 0