AI Trace
OtherVerified

Reviewed and published by trentmaziarz, May 11, 2026. Discovered and drafted by our automated research pipeline.

Cohere deployed Transcribe, an open-source automatic speech recognition model that converts spoken audio into text across 14 languages. It is available as a free API, a downloadable open-source model, and as a managed enterprise service through Cohere's Model Vault platform.

Details

Cohere Transcribe (released March 26, 2026) is a 2-billion-parameter encoder-decoder model that takes audio input and outputs text transcripts. It supports 14 languages including English, French, German, Chinese, Japanese, Korean, and Arabic, and claims the lowest word error rate on the Hugging Face Open ASR Leaderboard at 5.42% as of its launch date. Cohere plans to integrate Transcribe into its North enterprise agent platform to add voice capabilities to automated workflows. The model is available for download on Hugging Face under an open-source license, via the Cohere API for free up to rate limits, and through Model Vault for production deployments.

Products affected

Cohere TranscribeNorthModel Vault

Sources & Evidence

Cite this record

Trace Foundation. (2026). Cohere: Cohere deployed Transcribe, an open-source automatic speech recognition model that converts spoken audio into text across 14 languages. It is available as a free API, a downloadable open-source model, and as a managed enterprise service through Cohere's Model Vault platform (data as of 2026-05-11) [Data set record]. AI Trace. https://www.aitrace.org/r/practice/c5d0f19a-e60d-4f8f-a23b-330064ac3d9b. Accessed October 5, 2026.

Stable link
https://www.aitrace.org/r/practice/c5d0f19a-e60d-4f8f-a23b-330064ac3d9b
Data as of
May 11, 2026
Last verified
Not recorded

How to cite AI Trace

Other practices by Cohere

Have evidence about Cohere's AI practices? Submit a report.

Report a Sighting →