# Cohere Releases Top-Ranked Multilingual Transcription Model

> The new automatic speech recognition model from Cohere Labs sets a new benchmark on the Hugging Face Open ASR Leaderboard for multilingual performance.

Published by The Open Weights on Mar 24, 2026. Canonical: https://theopenweights.com/news/cohere-transcribe-03-2026-vg9w

## Key facts

- Company: Cohere
- Model: Cohere Transcribe 03-2026
- Version: 03-2026
- Category: Speech → Text
- Modalities: Speech → Text
- License: Other (Open weights, commercial use allowed)
- Architecture: CohereAsrForConditionalGeneration
- Precision: BF16
- Weights size: 4.1 GB
- Significance: notable
- Published: 2026-03-24
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/CohereLabs/cohere-transcribe-03-2026
- Canonical URL: https://theopenweights.com/news/cohere-transcribe-03-2026-vg9w

Cohere has released a new model for automatic speech recognition (ASR), Cohere Transcribe, immediately claiming the top position on the Hugging Face Open ASR Leaderboard. The model demonstrates state-of-the-art performance, particularly on challenging multilingual benchmarks like FLEURS (Few-shot Learning Evaluation of Universal Representations of Speech).

Trained on a large dataset of professionally transcribed audio, the model is designed to accurately convert spoken language into text across multiple languages. This capability makes it a powerful new tool for developers building voice-enabled applications, transcription services, and other features that rely on understanding human speech.

The release of a high-performing ASR model from a major AI lab like Cohere provides a strong alternative to existing leaders in the space, such as OpenAI's Whisper. As more powerful, openly-available models for speech are released, the barrier to creating sophisticated audio-based applications continues to fall for researchers and builders.

While the model's weights are publicly accessible, it is important to note the usage restrictions. Cohere Transcribe is available under a [Cohere Non-Commercial License](https://huggingface.co/CohereLabs/cohere-transcribe-03-2026), meaning it is intended for research and non-commercial projects rather than for deployment in production commercial applications.

## Get the model

- [Hugging Face](https://huggingface.co/CohereLabs/cohere-transcribe-03-2026)

## Sources

- [CohereLabs/cohere-transcribe-03-2026](https://huggingface.co/CohereLabs/cohere-transcribe-03-2026) — Hugging Face, Mar 24, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Cohere Releases Top-Ranked Multilingual Transcription Model", The Open Weights, Mar 24, 2026, https://theopenweights.com/news/cohere-transcribe-03-2026-vg9w