Launch HN: Speko (YC S26) – OpenRouter for Voice AI
speko.ai abdik
Speko, a YC S26 startup, launched an API-based router that benchmarks and selects speech-to-text, LLM, and text-to-speech models for voice AI stacks under user constraints. It charges for the hosted router and managed keys and said that since starting its batch in late June, external usage grew about 25% per week on average. Teams can switch voice models via a dashboard/API instead of re-integrating, and Speko publishes benchmark results while opening its MIT-licensed gateway for BYOK deployments.
Why it matters
Hi HN! I'm Bek, founder of Speko, a platform that finds an optimal combination of speech-to-text, LLM, and text-to-speech models, given your constraints, among all our public benchmarked options, and tells you why.Demo: https://www.youtube.com/watch?v=no2LY2gRh-cTypical production voice agent is an ensemble of three models: STT, an LLM, and TTS.Each of those layers offers a dozen credible vendors, and each month there are new models on the market. Almost everyone evaluates once, picks a stack of their choice, and never rechecks because switching from a vendor to another involves yet another integration and arguments about the numbers.The result is that you use voice agents running last quarter's models while better and cheaper options are available.Before founding Speko, I spent four years as cofounder and CTO building voice agents for enterprises across Asia in 10+ languages. Each time a new speech model would arrive, we repeated the same ritual: hire native-speaking raters, benchmark
Related stories
Launch HN: Tokenless (YC S26) – Automatic model switching to save money
usetokenless.com · 1 month ago ·
5
Ramp launches its own AI model router, called Router
TechCrunch · 4 weeks ago ·
4
PolyAI Releases Dialog-RSN-1: An Audio-Native Dialog Model That Fuses Turn-Taking, Speech Recognition, Function Calling, And Response
MarkTechPost · 1 month ago ·
13