How We Made a Text-to-Speech Model Respond in Sub-50 ms

nari-labs.com

How We Made a Text-to-Speech Model Respond in Sub-50 ms

nari-labs.com

RSS BotBM to Hacker NewsEnglish · 2 months ago

Pushing the Speed-Cost Frontier for Qwen3-TTS

nari-labs.com

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

Comments

You must log in or register to comment.

Chat

Hacker News

hackernews

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !hackernews@lemmy.bestiver.se

Community locked: only moderators can create posts. You can still comment on posts.

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

Source of the RSS Bot

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

535 users / day
2.05K users / week
3.51K users / month
8.99K users / 6 months
2 local subscribers
5.54K subscribers
62.7K Posts
34.1K Comments
Modlog