Tether AI releases ultra-fast speech-to-text model TranscribePsy
Tether CEO Paolo Ardoino tweeted that Tether AI's QVAC platform has officially launched the speech-to-text model TranscribePsy, featuring 250 million parameters and support for 25 European languages, specifically optimized for local execution on smartphones and laptops. On the iPhone 17 Pro Max Neural Engine, it takes just 1.65 seconds to transcribe a 10-minute audio recording. The model does not require cloud support, adopts a decentralized peer-to-peer architecture, and emphasizes local operation, high privacy, and cross-hardware compatibility.
