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

51–60 of 73 posts

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

#53

Post by abdik »

aleksiy123 wrote: post #52

Is this only for realtime tts use cases? Wondering if you also support some non realtime models.

yes, it does support, when you are creating an api key, you can point out narration or transcription use case, then you will be able to see. let me know how it goes or what use cases are thinking of for non-realtime models?

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

#54

Post by jvwww »

narrationbox wrote: post #7

> Typical production voice agent is an ensemble of three models: STT, an LLM, and TTS. To use a claudism , I would like to push back on this. The industry is very much moving towards one-model-does-all end to end trained similar to LLMs and VLMs. Mostly for latency reasons and partially because the results for the end to end trained models are just so much better than those using three pieces architectures. I think m…

This is not true in my experience. By and large, everyone uses the cascading voice stack.

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

#55

Post by dgreensp »

This looks really interesting.

I feel like there is a lot of room to build great voice-based agents that don't exist right now.

I have found that ChatGPT voice mode is unusable (e.g. hallucinates me saying things); Claude voice mode is usable, but very buggy around tool calling, and it often mishears things. And it only supports Opus, not Fable (though it looks like you don't support either of those). But I use it anyway.

Question, do any of your TTS options support increasing the speaking speed?

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

#58

Post by abdik »

alexcnwy wrote: post #57

why isn't openrouter gonna be the openrouter for voice ?

People who built or building voice agents immediately get this.

openrouter is the openrouter for audio models.

the conflation is "audio models" vs "voice ai", and the mental model that untangles it: think batch requests. text in, audio out (streamed, even). audio in, transcript out.

three questions inside the word "router":

1 - what gets picked: a model/voice, a provider of the same model, or the whole stack (stt + llm + tts) per call

2 - where it lives: an external http gateway, the agent platform (vapi/retell/livekit configs), or inside the live session

3 - when: session start, or mid-call

a voice agent is not a batch request. it's a live duplex session: turn-taking, barge-in, telephony legs, session state. the latency physics diverge too: a middleman hop in the media path is paid once by a batch request and on every conversational turn of a live call, so the media path wants a direct connection to the provider. a gateway that terminates at http can route the requests inside a call; it can't route the call.

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

#60

Post by abdik »

dgreensp wrote: post #55

This looks really interesting. I feel like there is a lot of room to build great voice-based agents that don't exist right now. I have found that ChatGPT voice mode is unusable (e.g. hallucinates me saying things); Claude voice mode is usable, but very buggy around tool calling, and it often mishears things. And it only supports Opus, not Fable (though it looks like you don't support either of those). But I use it an…

thanks! yes, some of them do, cuz speed is a per-provider capability, not universal. And, you can see it in the gateway code (minimax, hume, xai tts adapters all handle a speed param). that unevenness is actually a routing constraint by itself: "voices that support rate control" narrows the candidate list the same way language or latency does. and agree on the voice modes, the gap between the demo and a dependable agent is exactly why we started this. what are you building with it?
Post reply on HN