AI Briefing#real-time-inference
The latest AI and developer news about #real-time-inference, with the original source and a short summary.
The latest AI and developer news about #real-time-inference, with the original source and a short summary.
The model supports 43 languages and runs on phones, laptops, and browsers using Apache 2.0 licensed weights.
The 45B parameter model processes audio, video, and text in 160ms chunks while delegating complex reasoning to a larger backend model to maintain low latency.
The system is the first real-time generative surgical simulator trained on clinical cholecystectomy recordings to support live kinematic control.
The release includes a LiveKit-based Voice Agent SDK and speech models priced from $0.0035 per minute for transcription and $13 per 1M characters for TTS.
The model achieves ~1.8% average WER on Open TTS Leaderboard English sets and supports 51 style tags plus zero-shot cloning.
Visko's Orbis model achieves 1.07x playback speed on a single Cloud TPU slice using JAX and custom kernels.
ASLP-lab has released MeanVC2, a real-time voice conversion model supporting cross-gender and cross-language conversion.
JoyAI has released a 16B model that causally edits live video streams in real time based on natural language instructions.
OpenAI built a real-time, bidirectional system for natural voice conversations in GPT-Live.
Google's Magenta team has released Magenta RealTime 2, an open-weight model and inference engine capable of real-time music generation.