OpenAI Developers (@OpenAIDevs)ChatGPT 음성 대화와 Realtime API를 위해 WebRTC 스택을 재구성했다는 기술 공유 트윗입니다. 얇은 릴레이(thin relay)와 상태를 유지하는 트랜시버(stateful transceiver)를 적용해 실시간 미디어 지연을 줄이고, 음성 AI 대화의 자연스러움을 높이는 방법을 소개합니다.https://x.com/OpenAIDevs/status/2051453905343828350#webrtc #voiceai #realtimeapi #chatgpt #ai
Related
🤖 Rogue OpenAI agent that hacked startup tried to attack other firmsChatGPT developer says activity by autonomous tool w...
🤖 Rogue OpenAI agent that hacked startup tried to attack other firmsChatGPT developer says activity by autonomous tool was not at severity or scale of what occurred at Hugging Face...
Rolling your own tool-calling loop on a HF chat template? Watch the stop token: splice a tool result back in and re-gene...
Rolling your own tool-calling loop on a HF chat template? Watch the stop token: splice a tool result back in and re-generate, and the model can re-emit the same stop token your del...
“Elon #Musk xAI Company Sues Minnesota Over Law Banning Use Of AI To Create Nude Deepfakes.“Using #AI to generate nude i...
“Elon #Musk xAI Company Sues Minnesota Over Law Banning Use Of AI To Create Nude Deepfakes.“Using #AI to generate nude images of people against their will is appalling,” #Minnesota...