Hacker Newsnew | past | comments | ask | show | jobs | submit | thomasmol's commentslogin

Thanks for the shout-out and kind words!

Thomas here, maker of Spectropic and Audiogest. I am indeed focused on building a simple and reliable Whisper + diarization API. Also working on providing fine-tuned versions of Whisper of non-English languages through the API.

Feel free to reach out to me if anyone is interested in this!


Great looking API. Are you able to, or do you have plans, for there to be automatic speaker identification based on labeled samples of their voices? It would be great to basically have a library of known speakers that are auto matched when transcribing


Thanks! That is something I might offer in the future and is definitely possible with a library like pyannote. Would be really cool to add for sure.

I am also experimenting with post-processing transcripts with LLMs to infer speaker names from a transcript. It works pretty decent already but it's still a bit expensive. I have this feature available under the 'enhanced' model if you want to check it out: https://docs.spectropic.ai/models/transcribe/enhanced


Hi! Any plans to support streaming transcription with diarization?


Streaming is definitely on the to-do list! Its quite complex to stream both transcription + diarization, but we will get there eventually


Very interesting idea!

Currently I only have a discord channel for support and help, but your suggested approach of offering some included one on one consulting makes sense. I am gonna look into how I can implement this


Interesting thought, maybe I should add clear reasons why specific parts were included and how they work


I understand! Perhaps I should include more tools and tutorials on marketing as well?


Haha yes, was an issue with a rate limit on the Github API, should be fixed now! Didn't expect this amount of traffic :) Docs were built with Mintlify and the links to the repos in the docs will work once you have accepted the invite (after making a purchase).


Mmm strange, could you share on what page exactly? Edit: got rate limited by the Github api haha, fixed now :)


Getting a 500 on https://launchleopard.com/

<div class="flex h-screen flex-col justify-between scroll-smooth"><h1>500</h1> <p>Internal Error</p> <div id="svelte-announcer" aria-live="assertive" aria-atomic="true" style="position: absolute; left: 0px; top: 0px; clip: rect(0px, 0px, 0px, 0px); clip-path: inset(50%); overflow: hidden; white-space: nowrap; width: 1px; height: 1px;"></div></div>


Currently no.. Going to have to add that still. The Auth.js devs have said that they're going to include zero-config support for this


If you add support for that then I'll buy this.


I can understand that! What would you like to see included that would justify the price for you?


I honestly don't know. But from my perspective, this year I've spent probably in excess of 1000 hours working on my SaaS app, by contrast it took me maybe 3 days to setup all the required services to connect to Stripe, my analytics provider, etc.

Simply put, saving a few days of setup time does not cross the threshold of a product or service I would pay for. If this was something that would take me a few weeks or a month to put together myself then it would be a product I'd be willing to pay for.

Take a product like TailwindUI, it's expensive but also very worth it because it takes the time to build a professional landing page from 2-3 weeks of work down to 2-3 days of work.


You literally just valued your time at $13 per day.


This is a huge problem in the tech world I think. I think of myself as $30/hour against purchases and subscriptions - each hour something saves me is worth $30.

This boilerkit is worth $39 to me because it would definitely take me longer than a couple hours to build myself. Someone else has already put in the 100 to 1000 hours to make it a decent experience.


Yes you're right, some of this can be easily installed with a few commands!

However, the boilerplate also has a lot of other api routes, components and demo pages to setup an app.

If you're capable of easily setting that up yourself then this might not be for you, that's totally fine of course!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: