Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Speko (YC S26) – OpenRouter for Voice AI

speko.ai

Post reply on HN
Print view View original

21–30 of 73 posts

Re: Launch HN: Speko (YC S26) – OpenRouter for Voice AI

#22

Post by echelon »

bewareofscams wrote: post #18

Seems to be useless, the state of art for all categories is local on-device, voice model vendors are just rent seekers for those who know no better.

You're not the customer. This is for people building products that support thousands of users.

Linux on desktop is great for you, but this is a tool for people delivering solutions.

Re: Launch HN: Speko (YC S26) – OpenRouter for Voice AI

#23

Post by Tepix »

Ever since OpenAI launched their improved voice mode, I've been looking for a capable LLM with builtin voice-in and -out. Llama 4 was supposed to be it but turned out to be a dud. I haven't followed the topic closely lately, did I miss anything? Are there capable (!) open weights omni models that allow low latency voice chat? If so, what software do you use them with? Can you use a PWA on your phone? WebRTC? WebTransport?

Re: Launch HN: Speko (YC S26) – OpenRouter for Voice AI

#24

Post by bewareofscams »

echelon wrote: post #22
bewareofscams wrote: post #18

Seems to be useless, the state of art for all categories is local on-device, voice model vendors are just rent seekers for those who know no better.

You're not the customer. This is for people building products that support thousands of users. Linux on desktop is great for you, but this is a tool for people delivering solutions.

1) what if I told you I can leverage local models and serve thousands of users?

2) you know nothing about me

3) of course I am not! I do know better

Re: Launch HN: Speko (YC S26) – OpenRouter for Voice AI

#25

Post by owebmaster »

echelon wrote: post #22
bewareofscams wrote: post #18

Seems to be useless, the state of art for all categories is local on-device, voice model vendors are just rent seekers for those who know no better.

You're not the customer. This is for people building products that support thousands of users. Linux on desktop is great for you, but this is a tool for people delivering solutions.

> You're not the customer. This is for people building products that support thousands of users.

That's their dream. Your dream. The AI dream. Many would say it's AI psychosis.

Re: Launch HN: Speko (YC S26) – OpenRouter for Voice AI

#26

Post by maho »

Which model best allows me to transcribe speech that uses a lot of domain-specific terms? For example, when I say "Claude Code", it often gets transcribed as "Cloud Code", and I have to go back and edit or do a second pass with a traditional LLM (which can introduce additional errors).

Re: Launch HN: Speko (YC S26) – OpenRouter for Voice AI

#28

Post by omneity »

maho wrote: post #26

Which model best allows me to transcribe speech that uses a lot of domain-specific terms? For example, when I say "Claude Code", it often gets transcribed as "Cloud Code", and I have to go back and edit or do a second pass with a traditional LLM (which can introduce additional errors).

Good old Whisper allows you to enter a prompt with domain specific terms and it will use them for transcription.

Re: Launch HN: Speko (YC S26) – OpenRouter for Voice AI

#29

Post by jeffrwells »

maho wrote: post #26

Which model best allows me to transcribe speech that uses a lot of domain-specific terms? For example, when I say "Claude Code", it often gets transcribed as "Cloud Code", and I have to go back and edit or do a second pass with a traditional LLM (which can introduce additional errors).

I’ve had a lot of success in the past with fine tuning STT using synthetic data.

I was doing it for Veterinary (ambient recording -> SOAP notes) which has tons of complex domain-specific language AND it is critically important to get right.

“CPR” transcribing as “see pee are” just doesn’t cut it in that industry.

Post reply on HN