Cohere Transcribe Models by Cohere
2 models2026
Last refreshed 2026-07-13. Next refresh: weekly.
Details
ResearcherCohere
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models2
Released2026
Capabilities
MultimodalAll models
About
Cohere's automatic speech recognition (ASR) foundation models for high-fidelity transcription.
Decision facts
- Best fit
- speech recognitionvision and multimodal workcoding
- Capability starting point
- Cohere Transcribe Arabic (07-2026) with multimodal inputs
- Lowest tracked input
- Not tracked
- Closest related family
- Command
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
2 in view
Use when the workload needs speech recognition, 2B parameters, and multimodal inputs.
2026-07speech recognition2B parametersmultimodal inputs
Cohere Transcribe (03-2026)Current
Use when the workload needs speech recognition, 2B parameters, and multimodal inputs.
2026-03speech recognition2B parametersmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Cohere Transcribe Arabic (07-2026) | Use when the workload needs speech recognition, 2B parameters, and multimodal inputs. | 2026-07 | speech recognition2B parametersmultimodal inputs | Current |
| Cohere Transcribe (03-2026) | Use when the workload needs speech recognition, 2B parameters, and multimodal inputs. | 2026-03 | speech recognition2B parametersmultimodal inputs | Current |
Release Timeline
2 release groups2026-07
1 current
Cohere Transcribe Arabic (07-2026)
Currentspeech recognition2B parametersmultimodal inputs
2026-03
1 current
Cohere Transcribe (03-2026)
Currentspeech recognition2B parametersmultimodal inputs
Specifications(2 models)
| Model | Released | Parameters | Multimodal |
|---|---|---|---|
| Cohere Transcribe Arabic (07-2026) | 2026-07 | 2B | Yes |
| Cohere Transcribe (03-2026) | 2026-03 | 2B | Yes |
