惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Engineering at Meta
Engineering at Meta
The GitHub Blog
The GitHub Blog
博客园_首页
T
The Blog of Author Tim Ferriss
H
Hackread – Cybersecurity News, Data Breaches, AI and More
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
腾讯CDC
I
InfoQ
量子位
J
Java Code Geeks
P
Proofpoint News Feed
有赞技术团队
有赞技术团队
Webroot Blog
Webroot Blog
Martin Fowler
Martin Fowler
D
Docker
F
Fortinet All Blogs
云风的 BLOG
云风的 BLOG
V
Vulnerabilities – Threatpost
罗磊的独立博客
P
Proofpoint News Feed
T
The Exploit Database - CXSecurity.com
Cyberwarzone
Cyberwarzone
P
Privacy & Cybersecurity Law Blog
Last Week in AI
Last Week in AI
爱范儿
爱范儿
The Hacker News
The Hacker News
S
SegmentFault 最新的问题
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
博客园 - 三生石上(FineUI控件)
V
V2EX
Simon Willison's Weblog
Simon Willison's Weblog
AI
AI
Y
Y Combinator Blog
Security Archives - TechRepublic
Security Archives - TechRepublic
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
GbyAI
GbyAI
V
Visual Studio Blog
H
Heimdal Security Blog
S
Secure Thoughts
B
Blog RSS Feed
雷峰网
雷峰网
T
Tenable Blog
C
Check Point Blog
G
Google Developers Blog
大猫的无限游戏
大猫的无限游戏
D
Darknet – Hacking Tools, Hacker News & Cyber Security
Exploit-DB.com RSS Feed
Exploit-DB.com RSS Feed
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
A
About on SuperTechFans
Recent Commits to openclaw:main
Recent Commits to openclaw:main

Show HN

GitHub - steveking-gh/firmion: Firmion is DSL and engine for firmware image generation. GitHub - villagesql/villagesql-skills: Agent skills for VillageSQL - gemini-cli-extension; claude-code-plugin GitHub - flightdeckhq/flightdeck: Observability and control plane for AI agents. CSP Radar GitHub - Light-Heart-Labs/DreamServer: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. GitHub - Diplomat-ai/diplomat-agent-ts: What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks Code Block Selector - Visual Studio Marketplace Prometheus dependency graph — interactive showcase | Riftmap Show HN: I made a vi-like modal keyboard plugin for Figma GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser GitHub - dalemyers/Roar: A macOS CLI tool for notifications GitHub - district-solutions/open-agent-tools-coder: Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models. GitHub - progapandist/stripeek: A local TUI proxy for real-time Stripe API debugging, built for navigating complex payloads fast. GitHub - sir1st/hermes-desktop: All-in-one cross-platform desktop app for Hermes Agent — bundles Python + hermes-agent + hermes-web-ui GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach GitHub - nixys/nxs-universal-chart: The Helm chart you can use to install any of your applications into Kubernetes/OpenShift Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph Show HN: Continuity-auth – Respect-weighted rate limits for the open web GitHub - luml-ai/luml: AI lifecycle platform where engineers and agents track experiments, train models, and ship to production. GitHub - mrdanielcasper/CoreTex: A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. GitHub - clemg/pierre-github: Pierre's diffs.com and trees.software for Github GitHub - lyriks-io/unspaghettit: Behavior-driven AI development without prompt spaghetti. GitHub - sofumel/claude-handoff-revive: Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages. GitHub - dotexorg/saferpc: Typed, end-to-end encrypted RPC over any bidirectional channel. GitHub - BeeZeeAgent/beezee: Agent harness orchestration Legato Next.js Boilerplate for Internal Tools · CoreUI GitHub - clark-labs-inc/clark-hash: Clark Hash, 32x smaller searchable sketches for embeddings GitHub - ZeroPointRepo/youtube-mcp: The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Typing Mastery — climb toward 100+ WPM, deliberately GitHub - Andebugulin/Awareen GitHub - fayzan123/claude-workflow-composer: Visual desktop app for composing multi-agent coding workflows. Drag agents, attach skills and MCPs, wire handoffs, export to .claude/ GitHub - harshaneel/humanize: Best static AI text humanizer. Two research-grounded skills that work in any LLM (Claude, ChatGPT, Gemini, Codex): humanize beats perplexity-based detectors, ai-check produces forensic scoring with evidence-quoted flags. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature. GitHub - StackOneHQ/stack-nudge GitHub - nodes-app/swift-markdown-engine: A native AppKit Markdown editor for macOS, built on TextKit 2 and bridged to SwiftUI. We hardened an LLM agent. Each defense we added made it more exploitable. GitHub - alkait/WhatsKept: Agent-queryable WhatsApp history from an iOS backup — a single Go binary. GitHub - octelium/cordium: Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials. WAR.GOV/UFO Microfilm5 GitHub - scosman/videowright: Build animated explainer videos with your coding agent GitHub - dipankar/dscode: The code editor you can take apart. GitHub - zoharbabin/web-researcher-mcp: MCP server (Go) for AI assistants: web search, content extraction, academic/patent/news research. Multi-provider routing, 4-tier scraping, search lenses. Works with Claude, Cursor, and any MCP client. GitHub - ruvnet/RuView: π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. GitHub - scanaislop/aislop: Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 7 languages (TypeScript, JavaScript, Python, Go, Rust, Ruby, PHP). Sub-second, deterministic, no LLM at runtime. MIT-licensed. GitHub - kouhxp/cheap-im: CPU-only voice agent approximating Thinking Machines' Interaction Models demo GitHub - unprovable/OrchidMantis: Orchid Mantis — standalone framework for Zero-Knowledge Proofs of eXploit (ZKPoX). GitHub - MarcellM01/TinySearch: Shrink the web for your local LLMs! GitHub - TangibleResearch/Halgorithem: A Algo designed to detect AI Hallucitions GitHub - DO-SAY-GO/freelang: I love freelang GitHub - CarpseDeam/Aura-IDE: An AI coding harness that shaped itself - Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. GitHub - chojs23/concord: A feature-rich TUI client for Discord GitHub - tommyjepsen/awesome-ux-skills: UX & AI Product designs skills you can use today in Claude Code GitHub - aerf-spec/aerf: Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions. GitHub - kklimuk/docx-cli: CLI for AI agents (Claude, Codex) to read, edit, and comment on .docx files with full format fidelity. GitHub - Jwrede/tokentoll: Catch LLM cost changes in code review. Infracost for LLM spend. GitHub - samchon/ttsc: A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler GitHub - Higangssh/homebutler: 🏠 Manage your homelab from chat. Single binary, zero dependencies. GitHub - olalie/tapmap: See where your computer connects and what stands out on a live world map. GitHub - Diplomat-ai/diplomat-agent: What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks GitHub - Bajusz15/beacon: Open-source agent for secure remote access, monitoring, and deploys across home-lab and self-hosted machines like Raspberry Pi, N100, or any Linux server. Open web based TTY or tunnel Home Assistant and other local services securely without opening ports. BigTech AI News - Chrome 应用商店 GitHub - vinhnx/VTCode: VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. GitHub - michaelaz774/decision-engine: A decision operating system for startup founders, powered by Claude Code. Synthesizes wisdom from 25+ legendary founders and investors into interactive AI-driven decision frameworks. GitHub - Chrilleweb/dotenv-diff: Validate environment variable usage in your codebase GitHub - Lumen-Labs/brainapi2: BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications. GitHub - familiar-software/familiar: Let AI watch you work. Familiar lets your AI update its memory, skills, and knowledge by watching your screen. GitHub - skorotkiewicz/rudo: A small, elegant dock for Wayland GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. make sidebar/address bar rounded corner toggleable
Speechcap | Private Mac dictation with on-device AI cleanup
dhruwang · 2026-06-24 · via Show HN

Thoughts streamed clean.

macOS · Apple Silicon & Intel14-day Pro trial · no card

Privacy-first Mac dictation.

Push-to-talk Mac dictation. Hold a key, speak, release. Speechcap captures your raw speech, AI-cleans the fillers, and types flawless text into any app. Cloud Whisper out of the box, or flip to on-device on Pro. Starts at $3/month.

Free tier included · Pro from $3/mo

Re: Q4 launch sync

Fig. 01 · Idle · waiting for hotkeyFloats above any window. Never steals focus.

Step 01

Hold the key.

Right Option by default. Or fn, ⌘, or Caps Lock. Whatever you'll never press by accident.

Step 02

Speak naturally.

Filler words, restarts, second thoughts. All fine. Speechcap cleans them up.

Step 03⌘V

Push the launch sync to ThursdaySlack

Release. Done.

Text is pasted right where your cursor was. No window-switching, no copy-paste dance.

Transcription on-device

Whisper Large v3, full quality. No stripped-down variant.

AI cleanup on-device

The part competitors run in the cloud. Speechcap keeps it local.

Works without internet

Plane, SCIF, firewall. Same experience. Toggle Wi-Fi off and dictate.

Nothing logged

Zero telemetry. Transcripts stay local, invisible to us.

Re: Q4 launch sync

Push the launch sync to Thursday afternoon to review the marketing plan before we ship.

Transform · 12 words

↑↓ navigate applyesc dismiss

I

Improve

Polish wording and flow without changing what you said. The everyday default.

F

Formal

Polish for client emails, reviews, anything that needs to read like work.

N

Friendly

Warm + casual. For DMs to your team, comments on PRs, soft asks.

G

Fix grammar

Light copy edit only. Keeps your voice, removes the typos.

T

Translate

89 languages. Speak English, paste Japanese.

R

Refine prompt

Reshape a rough ask into a precise prompt for ChatGPT, Claude, or Gemini.

C

Custom

Type your own instruction. "Make it Hemingway," "as a haiku," whatever.

Mid-dictation transform

Hold , speak naturally, then tap a letter. F for Formal, I for Improve, T for Translate. Release the key and your transcript is rewritten before it ever lands on the page.

New note · Q4 launch sync

Idle · ready for hotkeyHold ⌥ · tap F mid-sentence · output is formalised

Spoken · EN

Push the launch sync to Thursday.

"Hello" · 12 of 89

HelloEN

你好ZH

こんにちはJA

HolaES

BonjourFR

안녕하세요KO

مرحباAR

नमस्तेHI

OláPT

HalloDE

ПривітUK

שלוםHE

+ 77 more

89 languages

Speak in any of 89. Paste in any of 89.

Auto-detects what you're saying. Translation is one keystroke away.

um so I think we should like, uh, push the launch sync sync to Thursday

Let's push the launch sync to Thursday.

Smart cleanup

Removes the ums. Keeps the you.

Filler words, restarts, false starts vanish. Smart punctuation. Context-aware formatting.

Speechcapflu-oh-cal

Anthropican-throw-pic

kubectlcube-cuttle

Söderbergsoh-der-berg

Vocabulary

It learns your jargon.

Names, acronyms, product codes, spelled how you spell them. Edit a dictated word once and Speechcap offers to remember it.

Privacy

Go fully private on Pro.

Cloud transcription out of the box. Switch to on-device Whisper on Pro. Audio never leaves your Mac.

2:14pSlack42w

11:42aGmail87w

9:08aVS Code18w

YestNotion142w

History

Every word, searchable.

Filter by app, by date, by transform. Re-paste with one click.

Spoken · trigger

"…and sign off."

Best, Maya Chen cal.com/maya/intro

Voice snippets

Say "sign off", paste the whole block.

Voice-triggered text expansion. A spoken trigger drops in your canned reply, meeting link, or signature. Set it up once, fire it in any app.

"user underscore id"

user_id

Speak the symbols

Say "rocket emoji", get 🚀.

Spoken-name substitution for emoji and punctuation runs deterministically. No AI call, no latency. Off by default for symbols (ambiguous), opt-in per-name.

Speechcap Team

Active · 5 seats · $30 / month · Renews May 18

J

Jamie ParkYou

jamie@northbridge.io

Owner···

A

Alex Tran

alex@northbridge.io

Admin···

S

Sara Vega

sara@northbridge.io

Member···

M

Marcus Lee

marcus@northbridge.io

Member···

01

Create a team

From Settings → Team in the app. Name it, pick seats, start the subscription. The owner pays once.

02

Invite by email

Each seat invite links to the recipient's Speechcap account. They instantly get full Pro.

03

Manage roles

Owner and admins can promote, remove, or transfer ownership. Members keep dictating either way.

04

Resize anytime

Add or remove seats from any device. Monthly or annual billing. No PPP discount, no per-seat haggling.

"I haven't typed a Slack message
in three weeks. I just hold a key and talk."

AT

Alex Tran · Engineering · early access

  • 2,500 words / week
  • Cloud Whisper · 89 languages · no model download
  • Always-on translation (89 target languages)
  • Hold-to-talk hotkey
  • Cleanup (fillers + punctuation)
  • Custom vocabulary
  • Local history

Most popular

Everything in Free, plus

  • Unlimited dictation
  • On-device offline mode (audio never leaves your Mac)
  • Context-aware AI cleanup
  • Transforms menu (improve, formal, translate, refine prompt…)
  • In-flight transforms while dictating
  • Cloud or on-device Whisper, your choice
  • Priority support

For teams

Everything in Pro, plus

  • Everything in Pro for every member
  • One subscription, central billing
  • Invite teammates by email
  • Admin + owner roles
  • Promote, remove, transfer ownership
  • Cancel or resize seats anytime

Questions, briefly.

Does it work offline?+

On Pro, yes. On-device Whisper transcribes without a network. Free tier and Pro cloud mode both need an internet connection.

Will it leak audio?+

Free and Pro cloud mode send audio to our transcription provider over an encrypted connection. It's discarded immediately after transcription. On Pro on-device mode, audio never leaves your Mac.

What about privacy with the Cloud model?+

Audio is encrypted in transit and at rest. We never train on your data. We don't share with third parties.

Can I use it without a hotkey?+

Yes. Toggle "tap to start" in Settings. We default to push-to-talk because it's less ambiguous about when we're listening.

How does the Teams plan work?+

$6 per seat per month, billed centrally. The owner pays once and invites teammates by email; every invited member gets full Pro features (unlimited dictation, on-device Whisper, transforms, translation). Admins can promote, remove, and transfer ownership; you can add or remove seats anytime. No PPP discount and no trial on Teams. Start a team from Settings → Team inside the app after installing.

Windows or Linux?+

Mac only today (Apple Silicon and Intel). Windows is next on the roadmap; Linux after that.

Stop typing. Start saying it.

14-day Pro trial. No credit card. Cancel any time, or fall back to Free and keep going.

07Comparisons

How Speechcap compares.

Picked between dictation apps for Mac? Here's how we stack up against the alternatives our users come from.

Experience the difference of true on-device intelligence.