Overview
Cabina transcriber v1 is a real-time speech-to-text model with stable timestamps, punctuation, and optional speaker labels for meetings, calls, and streams.
Description
Cabina transcriber v1 focuses on fast, accurate ASR with clean formatting. It streams partial and final results, aligns words with reliable timestamps, and supports diarization when multiple voices are present. Long-form audio stays coherent through sentence splitting and punctuation, and confidence scores help you trigger human review only where needed. It fits live captioning, call analytics, note-taking, and searchable archives.
About Cabina
We're a passionate team of Ukrainian innovators who believe in the power of simple, elegant solutions. We're building a platform that makes collaboration with AI easy and productive. Be better with us today, tomorrow & every time.
View Company Profile