arach

I've been building a little app on the side that allows me to primarily read my books in epub, mobi or pdf -> text format but generate readouts on demand for only the bits I want (highlight, paragraph, page, chapter) so that I can continue while I'm on the go, without having to bifurcate between apps - this might already exist but I made mine

Naturally, I also added the ability to highlight, leave notes and ... ask questions (via API)

Even with incredible models, it's a decent amount of work to get this to work nicely

https://openscout.app - a local first communication tool, for agent to agent communication and user to agent communication too

Error Error: No API found

but i love the idea

I bought it when it came out and enjoy using it. I have a STT keyboard powered by Parakeet that has a minimized mode ideal for phone terminals

https://x.com/usetalkieapp/status/2024342996322283734/photo/...

Combine this with a nice shortcut keyboard and then you're really flying - my favorites are XP Pen and DOIO 16

Ack for dictations but Gemini voice is fun for interactive voice experiments -> https://hud.arach.dev/ honestly blown away by how much Gemini could assist with with basically no dev effort

https://github.com/goodroot/hyprwhspr have you tried this? I have a nice 64GB new linux machine waiting to be set up for me to kick the tires on this

pretty sure it's awesome - sorry OP about mentioning another project, we're all learning here :)

Hex is great and not trying to pull you away from them - would love to get your pov when you give these a spin next time. email or DM me

My M1 16GB Mini and M2 16GB Air both deliver insane local transcription performance without eating up much memory - I think the M line + Parakeet delivers insane local performance and you get privacy for free

I initially built Talkie to talk to it like a crazy person when I was on long runs and ideas would pop into my head haha

Been a power user of SuperWhisper and Wispr Flow for a long time and eventually decided to unify those flows - memos & dictations, everything is a file and local first, BYOK

https://x.com/usetalkieapp/status/2022341320090775647/photo/...

native app uses Parakeet (v2 or V3) on iOS

Handy's great! I find the latency to be just a bit too much for my taste. Like half the people on this thread, built my own but with a bit more emphasis on speed

https://usetalkie.com

https://usetalkie.com - Parakeet and incredibly fast and made for devs

An exploration of infinite canvas, and voice assisted navigation

Powered by Gemini (bring your own key)

thanks man! I've actually gone a bit further with hooks and speech synthesis

https://hooked.arach.dev/ and https://speakeasy.arach.dev/ - it's a fun setup

nice, next step is to write a custom function that derives a useful but repeatable message from the hooks and put a little cache in front the Eleven Labs message gen. For example: "In {Project}, Claude needs your permission to run {command}"

That way you can stay comfortably in the free plan with awesome voice messages

I have a different voice for my laptop compared to my main computer and can also pick per project

My personal favorite hooks though are these:

  "Stop": [
  {
    "hooks": [
      {
        "type": "command",
        "command": "afplay -v 0.40 /System/Library/Sounds/Morse.aiff"
      }]}],
  "Notification": [
  {
    "hooks": [
      {
        "type": "command",
        "command": "afplay -v 0.35 /System/Library/Sounds/Ping.aiff"
      }]}]

Easy to implement -> can talk to ElevenLabs or OpenAI and it's a pretty delightful experience

Same as you and I was glad to see the status page - hit subscribe on updates

Claude user base believes in Sunday PM work sessions

this probably levels the playing field for a while, and then dramatically raises the bar over a longer period of time

as better engineers and better designers get more leverage with lower nuisance in the form of meetings and other people, they will be able to build better software with a level of taste and sophistication that wouldn't make sense if you had to hand type everything

this feels like language from another era

is yo taken?

that's a nice idea. i wonder if applying a bit of ai summarization / grouping logic could help present changes in logical sequences regardless of time or file proximity

would probably also make sense to add quick review actions in place - like ask a question to the gitlogue tool or the author during the playback

thanks for sharing, very interesting example

in other words, these limits will help introduce Enterprise (premium) plans?

fair enough - DS probably ran through data and came up with 5% and some weekly cutoff as a good starting point until they have better measures in place

my point is that 5% still a large cohort and they happen to be your most excited/creative cohort. they might not all want to pay a surchage yet while everyone is discovering the use cases / patterns / etc

having said that, entirely possible burn rate math and urgency requires this approach

5% of a large number is a large number - this why it's both a significant problem for them and why I'm thinking out loud about the downsides of discouraging good actors who happen to be power users.

that 5% is probably the most creative and excited cohort. obviously it's critical to not make the experience terrible for the 95% core, but i'd hate to lose even a minority of the power users who want to build incredible things on the platform

having said that, the team is elite, sure they are thinking about all angles of this issue

It’s tricky without seeing the actual data. 5% of a massive user base can still be a huge number so I get that it’s hard to be surgical.

But those power users are often your most creative, most productive, and most likely to generate standout use cases or case studies. Unless they’re outright abusing the system, I’d lean toward designing for them, not against them.

if the concern is genuine abuse, that feels like something you handle with escalation protocols: flag unusual usage, notify users, and apply adaptive caps if needed. Blanket restrictions risk penalizing your most valuable contributors before you’ve even discovered what they might build

"You're absolutely right!" i misread the announcement - thought everyone moved to primarily a weekly window but seems like 5hr window still in place and they're putting in place another granularity level control that DS teams will adjust to cutoff mostly bad actors.

correct me if I'm wrong, it's not like we have visibility into the token limit logic, even on the 5hr window?

I've noticed the frequent perf issues and I'm on the 20x plan myself - good point that you'd want to stop the bleeding or bad actors to make sure the majority have a better experience

if it affects only a minority of accounts, why not figure out how to special case them without affecting everyone else is the primary question I would ask myself if I worked on this

the principle: let's protect against outliers without rocking the behavior of the majority, not at this stage of PMF and market discovery

i'd also project out just how much the compute would cost for the outlier cohort - are we talking $5M, $100M, $1B per year? And then what behaviors will simply be missed by putting these caps in now - is it worth missing out on success stories coming from elite and creative users?

I'm sure this debate was held internally but still...