HackerTrans
TopNewTrendsCommentsPastAskShowJobs

irqlevel

no profile record

Submissions

Show HN: Rust EDR Agent for Linux with eBPF and macOS

github.com
1 points·by irqlevel·3 месяца назад·0 comments

Show HN: Nos – a hobby x86-64 C++ OS kernel running on real KVM clouds

github.com
3 points·by irqlevel·5 месяцев назад·0 comments

WhisperClip: 300ms Voice-to-Text on macOS (Fully Local)

whisperclip.com
2 points·by irqlevel·6 месяцев назад·1 comments

Show HN: Real-Time AI English Speaking Tutor

speaknetic.com
1 points·by irqlevel·7 месяцев назад·0 comments

Show HN: Real-time, open-source voice assistant in Rust

github.com
1 points·by irqlevel·7 месяцев назад·0 comments

Show HN: Rust Client Library for Gradium.ai TTS/STT API

github.com
3 points·by irqlevel·7 месяцев назад·0 comments

Show HN: Golang Client Library for Gradium.ai TTS/STT API

github.com
5 points·by irqlevel·7 месяцев назад·0 comments

Show HN: Privacy-First AI Document Chat for macOS (Offline RAG)

github.com
3 points·by irqlevel·10 месяцев назад·0 comments

Show HN: Privacy-First Voice-to-Text for macOS

github.com
31 points·by irqlevel·10 месяцев назад·14 comments

Show HN: Stream Voice-to-Text in Real Time on macOS [video]

youtube.com
6 points·by irqlevel·в прошлом году·3 comments

Show HN: Fully On-Premises Inference Server for Open-Source LLMs

localiq.ai
1 points·by irqlevel·в прошлом году·0 comments

Show HN: AI-Powered Stock Tracking and Analysis

stockadvisor.cc
1 points·by irqlevel·2 года назад·0 comments

Show HN: Grammar checker for text on website pages

sitechecker.cc
1 points·by irqlevel·2 года назад·0 comments

comments

irqlevel
·6 месяцев назад·discuss
Parakeet engine with Apple Neural Engine enables fast and accurate transcription: ~300 ms per sentence, ~700 ms per paragraph, and around 20 seconds for 1 hour of audio.

Transcribe audio files in MP3, WAV, M4A, FLAC, and OGG formats via drag and drop.

Full transcription history with searchable text.

Recording overlay, start-minimized option, and hold-to-talk mode.
irqlevel
·10 месяцев назад·discuss
This issue has been reproduced and fixed in version 1.0.44, now available on the website. Note that when you update the app, the models will be recompiled, so the app may briefly hang during recording. Each new app version → new hash → AI (MLX) code recompilation.
irqlevel
·10 месяцев назад·discuss
Thank you for the feedback. I will improve the onboarding and setup in the next app release.
irqlevel
·10 месяцев назад·discuss
Sorry about that — this feature is no longer available due to its cloud-based nature, but I plan to bring it back. The video was recorded before open-sourcing, so I’ll remove it to avoid confusion.

Update: Replaced the site video with a demo showing the actual app behavior.
irqlevel
·10 месяцев назад·discuss
Thank you for the feedback. I’ll work on reproducing the issue and will do my best to fix it.
irqlevel
·10 месяцев назад·discuss
Thank you — any feedback is appreciated. I want to be useful, not rich, so I made it open and free for everyone
irqlevel
·12 месяцев назад·discuss
Try https://whisperclip.com —it delivers low-latency, real-time voice-to-text streaming to any macOS app.
irqlevel
·в прошлом году·discuss
No, I use an in-house model based on some open analogs.