Granite Speech 5.0 is a new speech‑to‑text model that transcribes, translates, and attributes audio more accurately and faster. It improves transcription accuracy by 15% over its predecessor and adds real‑time translation for 12 languages, enabling developers to build multilingual voice apps with lower latency. The update also expands speaker diarization to 20 voices, boosting multi‑speaker workflows.
Opening Kapyn…