Speko (YC S26) launches OpenRouter for Voice AI, auto-switching STT, LLM, and TTS models
Launch HN: Speko (YC S26) – OpenRouter for Voice AI
Speko, founded by Bek, is a platform that benchmarks and routes between speech-to-text, LLM, and text-to-speech models. It finds the optimal combination based on your constraints (accuracy, latency, cost) and language/region, then switches models automatically via an API and gateway. The gateway can run in BYOK mode with no cloud communication. Speko publishes its benchmarks, including cases where its selections underperform. Since late June, external usage has grown ~25% per week.
We can literally go to this dashboard, switch the model, and it will do it for us.
- MikhailTal
What is the difference with Livekit Gateway? https://livekit.com/blog/introducing-livekit-inference
Or even something more managed like Vapi?
- webo
The benchmarks page seems interesting and something I can use to help make an informed decision. Can you talk about how you're measuring some of these? I imagine it needs to involve some human input.
- spmartin823
Does this include a turn taking API? It'd be great to have one API that could do "Conversation in a box". One of the biggest annoyances is daisy chaining many models together for turn taking, dumb models for immediate responses, with smarter models returning and taking over after.
- bewareofscams
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.
- 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).