MacParakeet

There are many dictation/transcription apps, but this one is mine.

Thank you for the oss support @greptile :) excited to try out /greploop and replace @coderabbitai slop

@kevinasrx Yessir, just build your own is the way

I’m just about to cancel my subscription to Wispr Flow. An app I use DAILY… Because I just built my own. And it’s just as good. It genuinely wasn’t that difficult. The capabilities are insane right now. All you need is a vision for what you want. The rest is “figure-out-able”.

0.6.7 released

222 stars and 22 forks 🎉

@1Umairshaikh iOS version for macparakeet

What are you building this Sunday? Drop your project URL Let's promote it

@dabit3 @DevinAI We would love to onboard devin to building MacParakeet and add him to the contributor. Thus far, it’s been codex and claudd. It’s free and opensource and comes with lots of delight. Give it a try and if you felt the delight, I would greatly appreciate the 200 max plan!

I'm giving away five $200 Max plans for @DevinAI If you're using tools like Claude Code, Codex, or Cursor and haven't tried @DevinAI, comment below with what you're building to be eligible. ⚡️

60 minutes of audio transcribed in 23 seconds. MacParakeet runs Parakeet TDT locally on Apple Silicon. Dictation, file & YouTube transcription, meeting recording. No cloud. No subscription. Free and open source. #macOS #OpenSource #DeveloperTools 🔗 Link in the comments

@jackfriks 💯

the difference between creating slop and creating beauty is caring about the little things.

@karrisaarinen I’m building for a delightful experience in open source everything

What if we built better software, not just more of it?

@marclou This is the way. MacParakeet was developed ai-first. Cli surface was developed together with the gui so that agents can test directly, get fast feedback, and course correct.

Making my SaaS AI-first: ✅ Open all API endpoints ✅ llms.txt & markdown docs ✅ CLI (new 🌟) ⬜️ MCP ⬜️ Generative UI ⬜️ Onboarding w/ paywall

@skeptrune My app was at $0 MRR until now :D

there's far more honor in $0 MRR than there is in grinding leetcode

@nico_laqua @emily_yuan_ Congrats on the milestone :) the interview was good

When @emily_yuan_ and I started Corgi, our goal was to build the insurance company we wished had existed when we were starting out. It took reimagining every layer of the stack (underwriting, claims, policy ops) to make it happen.

Today, @UseCorgi is announcing a $160M Series B at a $1.3B valuation led by TCV. This new round of funding will help us scale what we've built and expand into new verticals including trucking, payroll, and small business. This follows our $108M Series A that we announced 16 weeks ago, bringing total funding to over $268M.

- stats page is getting a ui polish - available now in 0.6.6 - cmux is awesome :)

@buildinpublic I was building macparakeet over the weekend. Now back to my 9-5 XD

What are you working on this week?

@FracSlap MacParakeet is a hybrid baby between wisprflow and granola XD local meeting recording has been shipped and more granola goodies on the way

Ripped out whisprflow and Granola is next. Loved both of those products and implemented them at our company but now they suck and aren't needed. Both are replaced with muesli which is open source and hosted on your machine. The real ROI will come in replacing granola. Instead of having Granola's shitty summaries, shitty api/mcp, and no ability to export transcripts—our raw transcripts will now feed into our database with all of our company data and business logic. Sensitive conversations will now stay on our servers and our agents will have access to raw transcripts with our company context on top of it. Will be a huge unlock for us.

@GitHub_Daily MacParakeet now supports whisper model so chinese/korean/japanese/etc can be transcribed!

GitHub 上一款专为 Mac 打造的纯本地语音转文字开源工具：MacParakeet，识别准确率颇高。 支持直接拖拽音视频文件，或者贴个 YouTube 链接，就能快速输出带时间戳和说话人标签的文稿。 还能同时录制电脑系统声音和麦克风，开会时一边看实时转写，一边做笔记。 GitHub：github.com/moona3k/macpar… 语音识别全程在本地运行，直接调用苹果的神经网络引擎，速度极快且音频数据绝不出本地。 如果有进阶需求，也可以接入本地 Ollama 或者各类大模型 API，帮我们自动生成会议摘要和整理排版。 提供了开箱即用的安装包，仅支持 Apple Silicon 芯片。需要一个快速、隐私优先的语音转文字工具的朋友，可以试试。

shorter utterances (0.3s) are now captured by parakeet model

@Sherifdeenolat2 Open source

How are you actually getting your first beta signups in 2026 when everyone's launching something?