Cohere Releases Open-Weight ASR Model 'Transcribe' at 5.4% Word Error Rate

2026-04-03T12:40:37.229Z·1 min read
Cohere has released Transcribe, an open-weight automatic speech recognition (ASR) model under Apache 2.0 license that achieves a 5.42% word error rate — accurate enough to replace closed speech API...

Cohere has released Transcribe, an open-weight automatic speech recognition (ASR) model under Apache 2.0 license that achieves a 5.42% word error rate — accurate enough to replace closed speech APIs in production pipelines.

Model Details

SpecificationValue
Parameters2 Billion
LicenseApache 2.0
WER5.42%
Languages14
API Namecohere-transcribe-03-2026

Supported Languages

English, French, German, Italian, Spanish, Greek, Dutch, Polish, Portuguese, Chinese, Japanese, Korean, Vietnamese, and Arabic.

Why It Matters

Until now, enterprise transcription has been a trade-off:

Transcribe breaks this trade-off by offering:

  1. Production-ready accuracy: 5.4% WER competitive with best closed APIs
  2. Self-hosted deployment: Run on your own GPU infrastructure
  3. Commercial license: Apache 2.0 with no restrictions
  4. Manageable footprint: Optimized for local GPU inference

Technical Achievement

Cohere says Transcribe "extends the Pareto frontier" — delivering state-of-the-art accuracy while maintaining best-in-class throughput within the 1B+ parameter cohort.

Impact

This could fundamentally change enterprise voice workflows by eliminating the dependency on cloud-based speech APIs, reducing costs, and addressing data residency concerns — particularly relevant for healthcare, legal, and financial services.

↗ Original source · 2026-04-03T00:00:00.000Z
← Previous: Slack Adds 30 AI Features to Slackbot: Fastest Product Adoption in Salesforce HistoryNext: Intuit's AI Agents Hit 85% Repeat Usage: The Secret Was Keeping Humans in the Loop →
Comments0