News for hackers. Stuff that matters.

Void_

Re:Gemini-3.5-Transcribe on Friday August 28, 2026 @08:20AM (#49477470)
I did the math based on our data from customers in https://whispermemos.com/ and it seems to be $0.12 per hour of input audio, with our average tokens/sec.

Scribe is $0.22.

If the accuracy is close to Scribe, I think it's a good deal.

Re:Claude Opus 5 on Saturday July 25, 2026 @05:20AM (#49045968)
Yeah, but I was reacting to idea of "frontend developer career coming to an end".

I guess kinda - the job will change from "frontend developer" to "UI inventor"..

Re:Claude Opus 5 on Saturday July 25, 2026 @12:34AM (#49044558)
I tried making a Things clone yesterday.

Spent maybe 7 hours of promoting with Fable.

I wanted to get drag and drop right, and I wanted good code architecture to start with.

It’s using TinyBase for data storage.

Here’s how far I got in 7 hours: https://focuslist.app

Yes, much faster than writing all of that by hand.

But prompting quality software into existence? No way. It would take at least another full time week to finish that app with all the detail I desire.

Re:It's getting harder to focus every day on Friday July 24, 2026 @07:54AM (#49034290)
I'm using an app called Focusmate (no affiliation) on a daily basis - scheduling 5-6 hour sessions per day.

You talk to a stranger for a few seconds, say what you're working on, and after 50 minutes you say goodbye. They stay on the video throughout the session, but muted.

It helps me focus because I always think "it's only 50 minutes".

Also, I recently deleted Instagram and it made a huge impact.

Re:Microsoft VibeVoice: Open-Source Frontier Voice AI on Tuesday April 28, 2026 @09:29AM (#47934310)
Our default is still OpenAI Whisper. Grok is just a choice for users who might prefer it.
Re:Microsoft VibeVoice: Open-Source Frontier Voice AI on Tuesday April 28, 2026 @09:10AM (#47934072)
I the past month or so, I added 2 models to my app Whisper Memos (https://whispermemos.com):

- Cohere Transcribe (self hosted)

- Grok Speech To Text (they provide an API, only $0.10/hr!)

They are both excellent. I'm not sure about this one. Would you like to see it in a consumer speech to text app?

Re:Cohere Transcribe: Speech Recognition on Tuesday March 31, 2026 @02:10PM (#47591297)
Just today I shipped support for this in Whisper Memos: https://whispermemos.com/changelog/2026-04-cohere-transcribe

Accurate and fast model, very happy with it so far!

Re:Aliens.gov ~ domain registered 17MAR2026 on Wednesday March 18, 2026 @10:30AM (#47426276)
According to Polymarket, there's a 16% chance US will confirm aliens exist: https://polymarket.com/event/will-the-us-confirm-that-aliens...
Are we gonna talk about that cookie banner? https://cleanshot.com/share/cDQ5RMkP
This just makes me want to play tennis right now. Such an addictive sports.
Not free, but Whisper Memos (https://whispermemos.com/) is about half the price
Re:Clicks Communicator on Friday January 02, 2026 @04:37PM (#46469696)
I just keep my iPhone locked up.

You can go to Screen Time and disable Safari and App Store.

You can protect it with a passcode, which is what I did.

After a few weeks I just got used to my phone being dumb.

Now these apps are unlocked, but the habit is there, and I use it for utility only.

I made WhisperType [1].

The price tag is $30/YEAR. The current MRR is about $700 and I'm paying $7/mo for Groq Whisper Turbo.

These apps really don't have any reason to be so pricey, it's all just margin.

1. https://whispertype.com/

Re:Grok 4 Fast now has 2M context window on Sunday November 09, 2025 @12:24AM (#45863142)
Half of USA voted for Trump. That should answer “who actually uses Grok”.

I personally use the best tool for the job, which Grok sometimes is.

Re:Extropic is building thermodynamic computing hardware on Thursday October 30, 2025 @05:09AM (#45757864)
Yes, the billionaire driving a Subaru Forester was my favorite part
Re:Extropic is building thermodynamic computing hardware on Wednesday October 29, 2025 @04:18PM (#45752491)
This gives me Devs vibe (2020 TV Series) - https://www.indiewire.com/awards/industry/devs-cinematograph...
Re:I've been loving Claude Code on the Web on Tuesday October 28, 2025 @03:25PM (#45737693)
I would love for them to open up the API to this.

I'd like to build an integration with Whisper Memos (https://whispermemos.com/)

Then I'd be able to dictate a note on my Apple Watch such as:

> Go into repository X and look at the screen Y, and fix bug Z.

That'd be so cool.

Re:Claude Haiku 4.5 on Wednesday October 15, 2025 @03:56PM (#45597619)
use claude-haiku-4-5-20251001
Re:Smartphones and Being Present on Monday October 13, 2025 @03:31PM (#45572395)
I've been running dumbified version of iOS for a few months now, and I'm very happy with it.

I removed every 'fun' app except for a few exceptions:

- ChatGPT, but mostly in voice mode, and with other people - as a party trick.

- Whisper Memos (https://whispermemos.com/), I record voice memos and they end up in my email, so I can continue with that idea when I'm on a computer (whether that is a prompt for AI, or a todo.)

- Bevel (https://www.bevel.health/), to track sleep factors, such as whether I wore a nasal strip

- Overcast (https://overcast.fm/), for playing podcasts.

- Liftosaur (http://liftosaur.com/), for tracking gym

- Basics like Banking, EV charging, Maps, Parking, Messages, Weather, Authenticator, Reminders, etc.

I removed App Store as well as Safari, so these apps is all I can do on my iPhone.

In the beginning, I set up a Screen Time code so I wouldn't be able to cheat. But in a few weeks I got used to it. So App Store and Safari are enabled again, but I never use them. (Maybe Safari is disabled. I have no idea to be honest.)

The biggest downside is I never know where my phone is. However, I'll gladly accept this downside.

And now of course we also run all life problems by ChatGPT.
I have mixed thoughts about audio journaling.

At first I was in love - I made an app around Whisper transcription model the weekend it came out. (Still working on it - https://whispermemos.com)

But when I try to read those recordings, they seem long and uninteresting.

I think the slowness of writing forces us to transform the thoughts/ideas into a format that has more substance.

So typing creates better distilled version of the text, and writing with one even more.

Recording audio just makes a raw stream of consciousness.

The process isn’t as therapeutic. It’s like stuffing food in your face instead of slowly chewing.

What are your thoughts on this?

Re:Claudia – Desktop companion for Claude code on Monday August 18, 2025 @01:47AM (#44937772)
Lots of apps named after the Whisper model (including mine - https://whispermemos.com/)

I wonder if I'll have to rename at some point.

We use very similar solution in https://reflect.app

Using the wa-sqlite library, and our own Mobx-based model layer similar to what Linear does.

I gave a short talk about it a few months ago https://www.youtube.com/watch?v=b0GKWzeyZko

I love this font! It's very well worth the price.
Re:A receipt printer cured my procrastination on Thursday June 12, 2025 @09:32AM (#44257604)
What helps me is to set up "morning routine" with tasks such as:

- get up with alarm - make the bed - shave - take vitamins - read 5 pages

Checking off 10 small tasks right in the morning sets me for a productive mood.

Here’s super fast and cheap alternative to Superwhisper:

https://whispertype.com

Re:Ask HN: What are you working on? (March 2025) on Monday March 31, 2025 @01:13AM (#43531324)
I just finished my Mac speech to text app: https://whispertype.com

Older »