Cohere Transcribe: the most accurate speech recognition model to date.

Cohere has announced Transcribe, a new open-source, state-of-the-art automatic speech recognition (ASR) model. The model was trained from scratch with a specific focus on achieving high accuracy by minimizing the word error rate (WER). It is designed for enterprise applications such as meeting transcription, speech analytics, and real-time customer support agents. This model represents a step toward powering broader enterprise speech intelligence and is available for download.