TOKENPOST
1 min read
Add as a preferred source on Google

Tether AI Research Unveils 254 Million-Parameter Speech Model

QVAC TranscribePsy is designed to run offline on devices, keeping audio on the device instead of sending it to cloud servers.

By Simon Yoon
Published
Smart glasses rest beside a compact humanoid robot head / TokenPost.ai (macro)
Smart glasses rest beside a compact humanoid robot head / TokenPost.ai (macro)

Tether AI Research announced QVAC TranscribePsy, a 254 million-parameter speech recognition model designed to process audio on devices without sending it to cloud servers.

The model can handle audio from smart glasses connected through Bluetooth or Wi-Fi. It can also run on a humanoid robot’s onboard processor.

TranscribePsy is intended to give developers an offline option for speech recognition, with low-latency processing that keeps audio on the device.

Simon Yoon

Reporter

Simon Yoon reports on blockchain technology for TokenPost. Send corrections or tips to info@tokenpost.com.

Loading…