Skip to content
JevDirectory.org

Voice turn-end detection with Jev

A Japanese demo that asks Jev 0.5 seconds after speech ends whether the turn is really over, then extends the hold time based on the returned score.

Category
Cookbooks & Demos
Format
Post
Published by
Community
Author
うえぞう
Added
2026-09-25
Last verified
2026-09-25

Highlights

  • Waits 0.5 s after the utterance ends, then asks Jev whether the turn is complete.
  • The score decides how much extra hold to add, shown as timeout=3.0 in the demo output.
  • Jev's own processing time was logged at 0.224 s in the recorded run.
  • Comes from the author of AIAvatarKit, a voice agent toolkit, rather than a benchmark.

Watch out

A social demo in Japanese with no published code or evaluation; treat the latency as one observed run.

Reactions & coverage

Posts, threads, and videos about this entry from around the web.

X: Voice-controlled computer use on a Mac

X: A computer assistant that listens

X: An always-on assistant with no wake word

X: Voice control over Fusion 360

I made this for fun. Wired a mic over Fusion 360: click, speak, Fusion runs the feature. @typesafeai ‘s Jev only decides if the utterance is a command.

Diogo Almeida
Diogo Almeida
TypeSafe AI
@CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x

Reply

Related terms

Glossary definitions related to this entry.

More like this

A video demo of Jev working through years of hoarded Twitter bookmarks in one pass instead of reading them by hand.
Cookbooks & DemosPost#community#x#video
Community
Alan's team built an intern-review console on Jev after 4,000+ applications: it checked 3,518 applications in 4 minutes 54 seconds and surfaced 20 for humans.
Cookbooks & DemosPost#community#x#video
Community
A ViZDoom agent with two Jev decision channels, navigation at 5 decisions per second and combat at 12, finishing a test run with 18 kills.
Cookbooks & DemosPost#community#x#video
Community
Back to all resources

From the community

Posts from builders shipping with Jev right now.

Follow @typesafeai

Cua's small System One models

A 706K-parameter form filler

cua open sourced a 706k param model that fills a whole form in one 50ms pass the llm agent doing the same form took 23 turns and 39.6 seconds the specialists are going to eat the generalists from the bottom

Cua
Cua
@trycua

1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use. Today we're open-sourcing CUA-S1-FORMS, the first in the family: github.com/trycua/cua

Image
Reply

Navigating Neo4j with Jev

Jev 这个 waitlist 还是很给力的,昨天申请,今天就能用上。 给已经拿到 API、但还不知道怎么玩的人整理了一份 Awesome Jev,目前我能确认到的 Jev 项目基本都在这里: 1. jev-ultrafast Browser Use 做的高速浏览器 Agent。Jev Show more

Image
思维怪怪
思维怪怪
@0xLogicrw

前 OpenAI 研究员 Diogo Almeida 创办的 TypeSafe AI 推出新模型 Jev。它有点像一个能读懂自然语言的超级分类器,不生成文本,只返回选项、分数和概率,专门给软件做判断。 普通大模型需要一个 token 一个 token 往外生成,Jev 则可以并行给出多个结果。TypeSafe 还用新的 RLCD

Reply

Reranking 33,047 catalog entries

拿 Jev 做搜索重排,我先泼一盆冷水:单独用,它没打赢向量检索 TypeSafe 的 Jev 这阵子很火,一堆项目拿它做重排。我们在 Agent Skills Hub 的 33,047 条目录上认真测了一次,164 条中英文真实查询,9,831 对分级标注,整套只花了 2.6 美元 三个结论 01|单独重排,约等于没赢 Jev 重排 bge-m3 Show more

Jason Zhu
Jason Zhu
@GoSailGlobal

有美团、阿里的老哥嘛? 试试加一路召回、重排(离线、近实时实现),我觉得有奇效 他在文本理解上 跟之前机器学习、llm很不一样 还能自动打标签做特征

Reply

Six uses that stuck after 60 days

Security decisions that fit Jev

This made me rethink where AI actually fits into security engineering. For purely engineering work, forget about ChatGPT or Claude. TypeSafe AI just released Jev, and I think it’s going to change how we build AI into security workflows. Instead of asking an LLM to “investigate Show more

TypeSafe AI
TypeSafe AI
@typesafeai

we are officially out of stealth! join the frontier and get access to Jev on our website (link on profile)

Reply