Hacker News: yujonglee

New comment by yujonglee in "Launch HN: Speko (YC S26) – OpenRouter for Voice AI"

yujonglee — Mon, 17 Aug 2026 19:41:22 +0000

cool! we have something similar implemented: https://github.com/fastrepl/anarlog/tree/main/crates/owhispe...

New comment by yujonglee in "Show HN: Maple-Preview – Ternary 20B MoE running at 120 tok/s on a iPhone"

yujonglee — Wed, 05 Aug 2026 10:21:47 +0000

amazing work! impressed with https://deepgrove.ai/chat

New comment by yujonglee in "The Conductor Rewrite: What They Changed to Make It Fast"

yujonglee — Wed, 24 Jun 2026 05:07:30 +0000

there is some overlap on how I built relay plugin: https://yujonglee.com/blog/hacking-tauri-for-designer/

Source code: https://github.com/fastrepl/anarlog/tree/d38413681a3c02f5ba3...

New comment by yujonglee in "Show HN: Compile-time model-id validation with declared capability"

yujonglee — Tue, 26 May 2026 14:21:49 +0000

fyi this use vendored openrouter models info:

https://github.com/yujonglee/openrouter-toolkit/blob/main/cr...

Show HN: Compile-time model-id validation with declared capability

yujonglee — Tue, 26 May 2026 14:20:07 +0000

Article URL: https://github.com/yujonglee/openrouter-toolkit

Comments URL: https://news.ycombinator.com/item?id=48280231

Points: 6

# Comments: 2

Show HN: Composable CLI for your meeting workflow

yujonglee — Wed, 01 Apr 2026 16:10:53 +0000

Hi, this is Yujong from Char (https://github.com/fastrepl/char).

This CLI is a repackaging of the audio/transcription pipeline that powers our desktop app. We noticed that some people build lightweight CLIs to record conversations and send them to tools like OpenClaw or other agents for transcription and workflow automation, so we wanted to make this more accessible as a standalone tool.

It provides a simple interface to record audio, capture system output, and run transcription across multiple providers (local: WhisperCpp, Cactus; cloud: Deepgram, Soinox, AssemblyAI, and more), using the same abstraction layer we use internally.

We thought this could be a useful building block for both humans and agents.

Curious to hear what others think!

You can find examples and documentation here: https://cli.char.com

Thank you!

Comments URL: https://news.ycombinator.com/item?id=47602786

Points: 3

# Comments: 0

Hacking Tauri for Designer

yujonglee — Sun, 22 Feb 2026 11:27:14 +0000

Article URL: https://yujonglee.com/blog/hacking-tauri-for-designer/

Comments URL: https://news.ycombinator.com/item?id=47110159

Points: 26

# Comments: 5

New comment by yujonglee in "Shipping 100 hardware units in under eight weeks"

yujonglee — Fri, 19 Sep 2025 16:40:51 +0000

Super impressed and inspired!

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Fri, 15 Aug 2025 17:35:34 +0000

kind of self-plug, but you might find https://github.com/fastrepl/hyprnote/blob/main/README.md interesting.

EDIT: typo

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Fri, 15 Aug 2025 06:59:23 +0000

It can run Whisper and Moonshine models locally, while also allowing the use of other API providers. Read the docs - or at least this post.

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Fri, 15 Aug 2025 05:47:22 +0000

what do you mean? this use-case is not llm. it is realtime stt.

also fyi - https://docs.hyprnote.com/owhisper/configuration/providers/o...

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Fri, 15 Aug 2025 02:20:12 +0000

sure. `owhisper pull --help`

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Fri, 15 Aug 2025 01:08:34 +0000

yes. metal is on

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Fri, 15 Aug 2025 00:34:06 +0000

Thank you!

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Thu, 14 Aug 2025 23:53:48 +0000

Its lot more than that.

- It supports other models like moonshine.

- It also works as proxy for cloud model providers.

- It can expose local models as Deepgram compatible api server

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Thu, 14 Aug 2025 23:51:39 +0000

probably end of this month or early next month. not 100% sure.

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Thu, 14 Aug 2025 23:51:11 +0000

we store data in R2 and range query sometime glitch... It might work if you retry it

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Thu, 14 Aug 2025 21:24:54 +0000

yeah we use whisper.cpp for whisper inference. this is more like a community-focused project, not a commercial product!

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Thu, 14 Aug 2025 21:19:59 +0000

got it. fyi if you run `owhisper pull --help`, this info is printed

New comment by yujonglee in "Show HN: OWhisper – Ollama for realtime speech-to-text"

yujonglee — Thu, 14 Aug 2025 20:54:50 +0000

It's open-source. Happy to review & merge if you can send us PR!

https://github.com/fastrepl/hyprnote/blob/8bc7a5eeae0fe58625...