#open-weight models

AI Hardware

Mistral's Voxtral TTS Clocks 70ms Latency — Open-Weight Punch to ElevenLabs' Gut

70 milliseconds. That's the latency Mistral claims for its new Voxtral TTS model on a 10-second clip. Open-weight, multilingual, and gunning for ElevenLabs — but is the hype real?

AI Hardware

China's Open AI Models Are Outpacing US Rivals—And It's Reshaping Who Builds What

Your next AI project might run on Alibaba's Qwen, not Meta's Llama. China's open models are cheaper, smarter, and everywhere—leaving US firms scrambling.