Rocket - Think it. Type it. Launch it.
Mini toolsCohere Transcribe
By Cohere
Cohere Transcribe is Cohere’s open-weights speech recognition model for converting spoken audio into text with high accuracy under real-world conditions. Cohere describes it as production-ready rather than just a research model, with local or managed deployment options through Model Vault. The model, named cohere-transcribe-03-2026, uses a Conformer-based encoder-decoder design, is 2B in size, and supports 14 languages including English, French, German, Spanish, Portuguese, Arabic, Chinese, Japanese, Korean, and Vietnamese. Cohere says it leads the Hugging Face Open ASR Leaderboard with a 5.42% average word error rate and is intended as a foundation for broader enterprise speech intelligence.
New
Audio
Gen 4
Overview
Cohere Transcribe is an open-source automatic speech recognition model for highly accurate audio transcription. Cohere says it is built for practical enterprise use, supports 14 languages, uses a 2B parameter Conformer-based encoder-decoder architecture, and currently ranks #1 on Hugging Face’s Open ASR Leaderboard for accuracy.
About Cohere
Cohere is a technology company specializing in Artificial Intelligence, Natural Language Processing, and Machine Learning solutions.
Industry:
Artificial Intelligence
Company Size:
51-200
Location:
Toronto, Ontario, CA
Website:
cohere.com
Tools using Cohere Transcribe
No tools found for this model yet.
Last updated: March 26, 2026
