Chubby (@kimmonismus)

OpenAI가 실시간 상호대화형 오디오를 목표로 하는 양방향(BiDi) 오디오 모델을 개발 중이라는 발표입니다. 기존의 턴 기반 음성 시스템과 달리 상대가 말하는 도중에도 AI가 중간에 반응을 조정하고 자연스러운 대화를 가능하게 하는 기술로, 음성 대화 경험의 패러다임 변화를 예고합니다.

https://x.com/kimmonismus/status/2029578248695226573

#openai #bidi #realtimeaudio #conversationalai

Chubby♨️ (@kimmonismus) on X

OpenAI Developing Real-Time Conversational Audio OpenAI is building a new bidirectional (BiDi) audio model designed to make AI conversations feel far more natural. Unlike today’s turn-based voice systems - where the AI waits for you to finish and can’t adjust mid-response - BiDi

X (formerly Twitter)

Chubby (@kimmonismus)

OpenAI가 실시간 상호대화형 오디오를 목표로 하는 양방향(BiDi) 오디오 모델을 개발 중이라는 발표입니다. 기존의 턴 기반 음성 시스템과 달리 상대가 말하는 도중에도 AI가 중간에 반응을 조정하고 자연스러운 대화를 가능하게 하는 기술로, 음성 대화 경험의 패러다임 변화를 예고합니다.

https://x.com/kimmonismus/status/2029578238750580912

#openai #bidi #realtimeaudio #conversationalai

Chubby♨️ (@kimmonismus) on X

OpenAI Developing Real-Time Conversational Audio OpenAI is building a new bidirectional (BiDi) audio model designed to make AI conversations feel far more natural. Unlike today’s turn-based voice systems - where the AI waits for you to finish and can’t adjust mid-response - BiDi

X (formerly Twitter)

Jordan Hall (@jordanhall)

부엌용 카운터탑 AI 음성 비서 개인 프로젝트 설명. 구형 iPad mini와 스피커/마이크 바, 3D 프린트 케이스를 결합해 HomePod를 대체하는 기기를 제작했고, OpenAI 실시간 오디오를 사용하며 웨이크워드 감지와 다중 사용자 음성 인증 기능을 갖추었다고 밝힘.

https://x.com/jordanhall/status/2015612840472609254

#openai #voiceassistant #realtimeaudio #wakeword #ipadmini

Jordan Hall (@jordanhall) on X

Been working on a fun side project - a countertop AI voice assistant to replace the HomePod in my kitchen. Combined an old iPad mini, a speaker/mic bar, and a 3D printed enclosure. Runs @OpenAI realtime audio with wake word detection, multi-user voice auth, and can delegate to

X (formerly Twitter)
Ever wondered how real-time audio capture works in modern web apps? Dive into our journey from ScriptProcessorNode to AudioWorklet and the unexpected hurdles we faced along the way. #WebAudio #RealTimeAudio #JavaScript https://www.doist.dev/building-ramble-2-capturing-audio-in-real-time/
Building Ramble #2: Capturing Audio in Real-Time

The unexpected challenges of streaming microphone audio through modern browser APIs

Migrate to FreeSimpleGUI

[FreeSimpleGUI](https://github.com/spyoungtech/FreeSimpleGUI) seems to be alive and well, and hopefully migrating shouldn't be much work.

Codeberg.org

Just tagged v0.0.5 for rtcirqus and uploaded it to PyPi.

This means rtcirqus is ready for more testing. So if you feel audacious and are curious about a tool that automatically increases or decreases rtprios for audio interfaces upon plugging in or out those devices then you might want to check out the project. Any help or feedback is much appreciated!

Project page: https://codeberg.org/autostatic/rtcirqus

#rtcirqus #LinuxAudio #RealTimeAudio

rtcirqus

rtcirqus, real-time config IRQ udev service, is a Python script that sets the real-time priority of IRQ threads of onboard and USB audio interfaces dynamically.

Codeberg.org
rtcqs v0.6.6 - rtcqs/rtcqs

# Changelog - Fixed the SMT check, it did not yield the expected result - Fixed a small typo in the SMT check description # SHA256sums `a41943de60cb39e51490e247f544e6f361bf7600357b6b6dd99dd714cd52b1a4 rtcqs_x86_64` `c78142eb4768c7b970570579478a6ad2716cb03b7b3291984fc962934a07bae2 rtcqs...

Codeberg.org
rtcqs v0.6.5 - rtcqs/rtcqs

# Changelog - Fixed typo (PR https://codeberg.org/rtcqs/rtcqs/pulls/11) - Added SMT check (fixes #12) # SHA256sums `073307361c47f083d3fe92a4c7ca17ced59e6af5aa18b65c920247805240ef0b rtcqs_x86_64` `5d5c1a10af33f534c6df306bb7b73cdd762c329646dd53d67e37763fc3b8caa6 rtcqs_gui_x86_64`

Codeberg.org