Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and cost

About

Hey HN, Toby from Nari Labs here. We've been working on making OSS speech models super-fast. Last year, we built Dia, the first OSS text-to-speech model capable of doing natural dialogue.

Discovery history

1. Show HN

   Sep 15, 2026 · 1 observations