I’m usually more a see both sides kinda guy but I agree - incompetent.

During COVID and after I ran a team that was majority remote and got a lot of flak from leaders and counterparts about their productivity.

I pulled up what they did. If each person gets X widgets created each week, passes quality gates and making each widget takes 15 min at best - you get the math. Nevertheless got a lot of “well it feels like” and “I just don’t feel their presence”.

Learned later in life how to better handle the perception of others, but this is one of the few places I don’t have room to be flexible. If you can’t run your team remote, you are not really managing them, you are at best drifting.

What’s really shocking is this and many of the competitors are all using OpenAI whisper - which came out in 2022. (Once upon a time, OpenAI really did open research)

It’s surprising in 2026 this is still the default “best” all rounder. Kudos to the early OpenAI team and the open community efforts / improved models since then.

no it's a really old and bad stt model i am using parakeet v3 here which is way superior

Superwhisper trains their own S1 models for this, you can use either a smaller local version of them or a beefier one in the cloud

Is there anything better for speech to text model?

Yes, parakeet. Ive switched all my apps to using it. Fantastic model

That is great! Just no fast inference like cerebras or groq support it

Parakeet is blindingly fast on modern hardware. My MacBook is just so fast, it's not even funny. But despite that, I still often use OpenWhisper because it just does better for accented voices. I also fine-tuned Qwen ASR on my voice, and that one is faster than Open Whisper, but I think I might even go back to Open Whisper eventually Because it still makes a lot of weird mistakes And I think it is over-indexed towards the fine tune And substitutes quite often wrong dictionary words for ambiguous words.

openwhispr dx is really bad, i made this product because i was tired that no one is working on accuracy and dx in general.

betterwispr main goal is to have accuracy and best dx possible.

Server side though?

parakeet v3 betterwispr uses that.

Regardless of the truth of the times, if you ever write a book with this view and cite your research where possible I suspect many of us would read it. The concept is fascinating.

I honestly don’t think deepseek is as good inherently as we treat it… but it thinks so much so fast it gets itself there. I’ve been super impressed.

If you can give it a measurable objective, load up $5 or so and just leave it for a few hours it usually gets there.

I dropped back to Opus 4.8 and it's so much better. Opus 5 was - to your point - actually driving me insane.