← 최신 프로덕트

Speko (YC S26)

OpenRouter for Voice AI. Every voice model is benchmarked in English. Your users don't speak English. Speko measures 83 speech and language models across 17 languages, then routes each session to the one that actually wins. 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.

speko.ai 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Moonshine Open-Weights STT models

    github.com

    higher accuracy than WhisperLargev3

    Hacker News316점

  2. We Help Voice AI Handle Group Conversations

    github.com

    Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and the agent's own TTS echo never trigger it. No wake word, model-agnostic, drop-in for LiveKit, Pipecat, ElevenLabs, Twilio, and OpenAI. The layer your VAD and turn detection are missing.

    Hacker News5점

  3. Voice gender classifier for European voice AI (1MB

    huggingface.co

    ONNX, 4ms)

    Hacker News5점

  4. OSS voice based conversational API with <1sec latency and other nuances

    bolna.dev

    Over the past few months we've been working on building a platform to build, scale and monitor voice based LLM applications.

    Hacker News8점

  5. LLM Round‑Trip Translation Benchmark

    github.com

    When a model translates out of English and then back to English, how much meaning and voice does it keep? Each model does both steps (English → target language → English).

    Hacker News6점