Model reference · open weights

cohere-transcribe-03-2026

cohere-transcribe-03-2026 is an open-weight audio or speech model from Cohere. cohere-transcribe-03-2026 (BF16) weighs 4.1 GB; the smallest configuration that runs it is RTX 3060 12 GB.

• Cohere Transcribe is an open-source automatic speech recognition model developed by Cohere with 2.1 billion parameters.
• It is designed for efficient audio-to-text transcription and supports 14 languages, including Arabic, German, Greek, English, Spanish, French, Italian, and Japanese.
• The model is released under the Apache 2.0 license and is intended for offline inference or production serving via supported libraries.

Summary of the CohereLabs/cohere-transcribe-03-2026 model card, 2026-10-01

Hugging Face ↗GitHub ↗