Nari Labs Blog company blog

How we made a text-to-speech model respond in sub-50 ms

by Nari Labs Team nari-labs.com published 2026-08-197 min read

10 RPS with p95 TTFA under 50 ms on a single H100: how we optimized Qwen3-TTS serving.

Points

171

HN comments

44

Submissions

1

Cited by

0 commenters

AI & Machine LearningSoftware Engineering2026

Related posts from the same era

Statement on US government directive to suspend access to Fable 5 and Mythos 5

Anthropic20263,158 points2,314 commentscited by 11 details

Astra can read and write weights to improve Qwen

RRikiya Takehi20262,960 points899 comments details

HackerTube: YouTube built from videos recommended by HN

karpathy20262,889 points642 comments details

Claude Fable 5

Anthropic20262,626 points2,159 commentscited by 10 details

Claude Code is steganographically marking requests

Thereallo20262,445 points750 commentscited by 3 details

My AI skeptic friends are all nuts

Fly.io Blog20252,356 points2,826 commentscited by 13 details