Cohere Releases Open-Weight ASR Model 'Transcribe' with 5.4% Word Error Rate, Apache-2.0 Licensed
Cohere has released Transcribe, an open-weight automatic speech recognition (ASR) model that achieves a 5.42% word error rate (WER), outperforming OpenAI's Whisper Large v3 and ElevenLabs Scribe v2.
Key Specifications
| Specification | Detail |
|---|---|
| Model name | cohere-transcribe-03-2026 |
| Parameters | 2 billion |
| License | Apache-2.0 (commercial use OK) |
| WER (avg) | 5.42% |
| Languages | 14 (English, French, German, Italian, Spanish, Chinese, Japanese, Korean, Arabic, etc.) |
| Deployment | Self-hosted on local GPU infrastructure |
Performance Comparison
| Model | WER |
|---|---|
| Cohere Transcribe | 5.42% |
| ElevenLabs Scribe v2 | 5.83% |
| Qwen3-ASR-1.7B | 5.76% |
| OpenAI Whisper Large v3 | 7.44% |
Why This Matters
The ASR market has been dominated by closed APIs (OpenAI, ElevenLabs, Google) that offer accuracy but create data residency risks and lock users into external services. Cohere's Transcribe:
- Runs on local GPU infrastructure — no data leaves the organization
- Licensed under Apache-2.0 — free for commercial use from day one
- Designed for production pipelines (RAG, agent workflows, audio search)
- Manageable inference footprint for local deployment
Use Cases
- Enterprise voice-enabled workflows
- Audio transcription pipelines
- RAG (Retrieval-Augmented Generation) with audio inputs
- AI agent workflows processing voice data
- Meeting transcription and analysis
Analysis
Transcribe is significant because it closes the gap between open-source and proprietary ASR. At 2B parameters with Apache-2.0 licensing, it's practical for production deployment on commodity hardware. For organizations building AI agent pipelines that process audio, Transcribe offers a path to high-accuracy transcription without the latency, cost, and data privacy concerns of cloud APIs.
The 14-language support including Chinese, Japanese, and Korean makes it relevant for the Asian enterprise market, where data residency requirements are often stricter.