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

Cohere has introduced Transcribe, a new speech recognition model for generating highly accurate audio transcripts. The company positions it as the most accurate model currently available, designed for enterprise-level applications. It is part of Cohere's suite of generative models, which also includes the Command family of language models and the multilingual Aya Expanse. Transcribe is built to handle challenging audio conditions and is presented alongside other advanced retrieval models like Embed and Rerank.