@mattpocockuk What makes it so good?
Last time I looked into it, it seemed like it’s mostly a way to enforce result types and pattern matching/tagged errors.
But that can be done in ~200 LOC, so I must be missing something 🤔
English
Hubab
185 posts
Hubab
@hubab33
Building @get_utter https://t.co/fVnqq0BwGs
West Mids, UK Katılım Temmuz 2024
352 Takip Edilen80 Takipçiler
Think I might need to revisit Effect on my YouTube channel
There is literally no better AX for building backend stuff in TypeScript.
Once you see it through that lens it's addictive
English
@FracSlap 💯 Nova-3 is the move for this.
Solid speaker diarization, $200 in free credits, and it plugs into most dictation + meeting recording tools that support BYOK.
Quick guide to get the free credits + API key:
utter.to/docs/guides/us…
English
Deepgram Nova-3
Don't say I never put y'all on game!
Alex Holman@AlexMultiFamily
@FracSlap The issue with Muesli and others is that they can't detect the speaker, which is pretty critical for analysis. We set up something similar, and the agent kept confusing what we would say and what a customer would say.
English
@FracSlap All value accrues to model providers unless apps create lock-in. Providers will probably ship this feature in their apps in <1yr.
If you want dictation + meeting recording, try Utter: data on disk, live transcripts, speaker labels, mid-meeting Q&A.
x.com/hubab33/status…
Hubab@hubab33
A simple meeting copilot: • See who said what (live) • Take notes in one place • Ask questions about the conversation instantly No fluff. Just works. Free with your API key.
English
Granola has raised $200 million at $1.5B valuation but you can't export transcripts without third-party tools.
Incredible.
Joe Dillon, CPA@joedilloncpa
@FracSlap @MatznerJon Thanks for this. Btw can export Granola transcripts to .md file with Raycast on a Mac but would love to not have to jump through hoops
English
@AlexMultiFamily @FracSlap From experience building something similar: speaker detection accuracy mostly comes down to model choice.
Local models still aren’t good enough yet. For reliable detection you need to use top hosted models like Deepgram Nova 3 or ElevenLabs Scribe.
x.com/hubab33/status…
Hubab@hubab33
A simple meeting copilot: • See who said what (live) • Take notes in one place • Ask questions about the conversation instantly No fluff. Just works. Free with your API key.
English
@FracSlap The issue with Muesli and others is that they can't detect the speaker, which is pretty critical for analysis. We set up something similar, and the agent kept confusing what we would say and what a customer would say.
English
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.
English
@FracSlap 💯 local-first wins. Data on disk > data locked in apps.
Built this into Utter for dictation + meetings: live transcripts, speaker labels, ask questions mid-meeting, save everything to disk.
Use BYOK or local models for free. Your data stays yours.
x.com/hubab33/status…
Hubab@hubab33
A simple meeting copilot: • See who said what (live) • Take notes in one place • Ask questions about the conversation instantly No fluff. Just works. Free with your API key.
English
@ingoa_dev Thanks for sharing but it’s honestly an unrealistic failure mode, the script is very simple.
The app defaults to you having to manually login when refreshing cookies, if you add your credentials in the app settings it can automate that step.
English
OpenASO is live 🚀
A free, open-source alternative for App Store Optimization.
Track keywords, research competitors, analyze reviews, translate/respond to users, and export data for AI analysis.
openaso.thirdtechapps.com
🧵 What you can do with it:
English
@delulucoder It’s from public App Store, iTunes Search and Apple Ads APIs
English
@ingoa_dev Thanks
Web login is so Apple ads web cookie can be used to fetch keyword popularity and ASC key is for replying to reviews. Both are optional and all data stays on device
English
@PKodmad Yeah, ASO can feel like a black hole because it’s so tedious.
I just released a free tool to automate most of it, give it a try.
It can research competitors, keyword rankings, reviews, and screenshots, then help turn that data into ASO recommendations.
x.com/hubab33/status…
Hubab@hubab33
OpenASO is live 🚀 A free, open-source alternative for App Store Optimization. Track keywords, research competitors, analyze reviews, translate/respond to users, and export data for AI analysis. openaso.thirdtechapps.com 🧵 What you can do with it:
English
Day 16 of distributing Jodu app.
Downloads in 10 days of May have surpassed downloads from all of April. 🙌
I’m not sure if my ASO tweaks improved my app’s standing or not. ASO is such a black hole.
I’m losing 50% of users in onboarding. Built a stronger onboarding flow.
Weekends are not strong building days. Still found some time to build out the carousel feature. Some more changes before shipping it tomorrow.
Brainstormed new content strategies. Need to widen the funnel even more.
Microgoal - 100 downloads a week
PK 🐢 👩🏻💻@PKodmad
Day 11 of distributing Jodu app. More n more downloads from ChatGPT. Love to see. A chunk of downloads from Germany. Focused on some basic localisation for this language. Bought @TryAstroApp and focusing on keyword ASO optimisation. Pushed 2.0.5 with some new app improvements.
English
@dev_alexandrum Everything is stored locally on your device. If iCloud is enabled, Apple syncs that app data across devices signed into the same Apple ID. There’s no account or login system on our end, and cross-device transcript history comes from iCloud syncing, not our servers.
English
i feel like i don’t think linearly enough for speech to text prompting.
i frequently change wording as i write so the pressure of having to voice the right prompt first try is frustrating
gabriel@gabriel1
ultra fast voice & language models will be even more important for everyday work use your voice to work, and immediately see the result live on your screen. go between apps, navigate complex interfaces, create custom interfaces to preview, all instant
English
@interplato @stefanoscalia It comes from public App Store APIs/search endpoints plus publicly accessible metadata/reviews/screenshots.
OpenASO basically handles gathering + structuring all that data for you locally, then MCP/skills analyze it.
The repo probably explains it better than I can in a tweet 😅
English
@hubab33 @stefanoscalia Really? I’d love to play around with that data. Could you point me to these links?
English
Give utter.to a try, this was one of the main workflows I built it around.
You can create prompting modes (prompt + model + shortcut) that rewrite messy dictation into clean specs/prompts before pasting.
Free w/ local models or your own API keys, plus a hosted free trial.
English
@interplato @stefanoscalia Fair point. I should probably do a side-by-side.
A lot of the underlying ASO data is already public/free to access. OpenASO stays free because the collection happens locally, so there aren’t ongoing server costs.
The MCP + skills part grounds analysis in real App Store data.
English
@hubab33 @stefanoscalia Given how many people rely on paid alternatives for such a long time…. It’d be great proof if you showed your tool vs a paid tool to
Build confidence
English
@gabriel1 I do the same.
Lately, I’ve started using a post-processing prompt trained on my own dictation patterns to see if the model performs better when it has less ambiguity to resolve.
Hubab@hubab33
Because my dictations are saved to disk, I can have Codex analyze recent prompts and auto-generate a better post-processing prompt, personalized to my prompting/speaking style. My rough voice input gets cleaned before it hits the coding agent. Tiny workflow win that compounds.
English
when i voice prompt, i yap for 10 minutes straight and change my mind 3 times in the middle of the yap, and send it without reading
yap enough tokens for the picture to be complete, it understands well when you change your mind in the middle. ai is smarter than you think
Alex@dev_alexandrum
i feel like i don’t think linearly enough for speech to text prompting. i frequently change wording as i write so the pressure of having to voice the right prompt first try is frustrating
English
@Thomasbcn Agreed on the small market point. That’s why I chose fully free and open source.
English
Built your iOS app with Codex? Nice. Now comes the hard part: getting downloads 😅
Built OpenASO.thirdtechapps.com with Codex to automate ASO: keyword tracking and metadata optimization to get more App Store search downloads. Works in Codex via MCP + skills.
#OpenAIDevDay2026
English