DeepL's Aure model carries speaker tone into real-time translation
Aure runs in DeepL Voice meetings, in-person mode, and the API across eight languages, replacing a static voice sample.
Stories per day · 30 days
2 RSS
Relatedaure1autonomous-driving1benchmark1deepl1game-worlds1gpt-6-astra1inference1lfm1lidar1liquid-ai1matrix-game1minigames1model-weights1speech-translation1token-pruning1transformers1video-models1vision-language-agents1
14 stories, newest first · one card per story
Stories tagged #real-time
FWL-ToPM Enables Real-Time Full-Waveform LiDAR Transformers
FWL-ToPM provides over 8x speedup and nearly 9-point F1 gain on Ghost-FWL benchmark.
Gym-Anything-RT benchmarks vision-language agents in real time
GPT-6 Astra passed 9.0% of 100 real-time minigames, rising to 75.0% when the environment was paused.
Liquid AI launches RIPL inference engine for sub-50 ms LFMs
The fetched page is only a cookie notice, so engine details beyond the headline are unavailable.
Matrix-Game 4.0 renders playable worlds at 480p and 60 FPS
An engine plus distilled video renderer reports 112 ms latency on one RTX 5090, with code and weights released.
WorldSonus: Bringing Sound to Worlds
WorldSonus adds real-time, controllable spatial stereo audio to interactive world-model video streams.
Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation
Two-step flow denoising cuts VLA inference from 61.6 ms to 22.0 ms with a small performance drop.
One Basis to Animate Them All: Gaussian Blendshape Distillation for Real-Time Avatars
GALA approximates neural 3D avatar animation with linear blendshapes, cutting CPU cost up to 1,000x and reaching 60fps on mobile.
HelixWorld: A Real-time Interactive Audio-Visual World Model
HelixWorld is a real-time audio-visual world model running joint rollouts at 24 FPS.
WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon
WorldPlay2 combines hybrid controls, compressed memory, and Stable Forcing for real-time long-horizon world models.
**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**
NVIDIA released Nemotron 3 Diarization, a real-time AI model for identifying multiple speakers in audio streams.
USN-8729-2: Linux kernel (Raspberry Pi Real-time) vulnerabilities
Ubuntu patches multiple Linux kernel vulnerabilities in the Raspberry Pi real-time variant via USN-8729-2, including the Microsoft Azure Network Adapter driver.
LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows
LynnReal-Omni unifies controllable video generation tasks in a 32B multimodal diffusion transformer, with a 27B Flash variant rendering 540p clips in 377 ms.
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
Vidu S2 delivers real-time 720p interactive avatar generation plus real-time video editing with style, clothing, character, and background replacement.