all AI news
Seamless Communication
Simon Willison's Weblog simonwillison.net
A new "family of AI research models" from Meta AI for speech and text translation. The live demo is particularly worth trying - you can record a short webcam video of yourself speaking and get back the same video with your speech translated into another language.
The key to it is the new SeamlessM4T v2 model, which supports 101 languages for speech input, 96 Languages for text input/output and 35 languages for speech output. SeamlessM4T-Large v2 is a …
ai ai research communication demo facebook family get back language llms meta meta ai research seamlessm4t speaking speech text the key transformers translated translation video webcam