Microsoft has released VibeVoice-ASR as part of the VibeVoice family of open source Frontier voice AI models. VibeVoice-ASR is described as an integrated speech-to-text model that can handle up to …
Tag:
Audio
-
-
Jada Jones/ZDNET Follow ZDNET: Add us as a favorite source On Google. ZDNET Highlights xMEMS designs and manufactures small audio and cooling chips. The company’s audio chips can replace entire …
-
Nina Raymont/ZDNET ZDNET Highlights The NextSense earbuds monitor brain activity using EEG. The Sleep Earbuds claim to use EEG for restorative sleep. They cost $399 and are available for preorder. …
-
Klipsch debuted the HP-1 headphones at CES 2026, and this model is the first closed-back, wireless ANC headphone within the company’s Atlas lineup. The HP-1 features coaxial drivers, wood finish, …
-
Switchbot is joining the AI voice recorder bandwagon, introducing its own clip-on gadget that captures and organizes your every conversation. Switchbot AI MindClip, announced at CES, records spoken information from …
-
Creative Stage Pro Soundbar ZDNET Highlights The Creative Stage Pro Soundbar is available on Amazon for $170. This cost-effective soundbar is excellent at producing clear dialogue. The Stage Pro subwoofer …
-
Generative AI
Meta AI Open-Sourced Perception Encoder Audiovisual (PE-AV): Audiovisual encoder powering SAM audio and large-scale multimodal retrieval
Meta Researchers Introduce Perception Encoder Audiovisual, PEAVAs a new family of encoders for joint audio and video understanding. The model learns aligned audio, video and text representations in a single …
-
Generative AI
Meta AI Releases SAM Audio: A State-of-the-Art Unified Model That Uses Spontaneous and Multimodal Signals for Audio Separation
Meta has released SAM Audio, a quick-driven audio separation model that targets a common editing constraint, separating a sound from a real-world mix without creating a custom model per sound …
-
Generative AI
StepFun AI Releases Step-Audio-R1: A New Audio LLM That Finally Benefits from Test Time Compute Scaling
by ai-intensifyWhy current audio AI models often perform poorly when they generate long arguments instead of basing their decisions on actual sound. The StepFun research team has released Step-Audio-R1, a new …