Cohere / SOURCE-LINKED MODEL RECORD

Cohere Transcribe Arabic

A model record assembled from original source observations. Review the exact artifact and its evidence before choosing a deployment.

Hosted modelverifiedObserved Oct 12, 2026
Input types
audio
Output types
text
Observed context window
Not established
Source release date
Jul 7, 2026

Know the exact model.

The canonical record is coherelabs:cohere-transcribe-arabic. Capabilities and context limits reflect source observations; the limits of a particular inference endpoint may differ.

Inclusion in the radar does not mean this model is served by Flonno. For the model currently available through our API, see Qwen3.8 Flash 27B and API pricing.

Artifact evidence

https://docs.cohere.com/v2/changelog/transcribe-arabic|cohere-transcribe-arabic|release

official changelog · Pinned artifact · Official provider announcement. First observed Oct 12, 2026; last observed Oct 12, 2026.

Open original artifact source ↗

Evaluate it for your workflow.

Pin the artifact and inference configuration. Use representative inputs with a written answer rubric, then record accepted results, errors, complete request time and token usage. Keep output budgets and concurrency explicit.

Benchmark results apply to their recorded version and method. They do not transfer automatically to a different runtime or a quantized derivative.

Explore practical comparison guides →

Benchmark provenance

Read the methodology →

No source-linked benchmark measurements are available for this exact model artifact.

Verified lifecycle updates

Source publication date
Cohere / release

Cohere Cohere Transcribe Arabic released

Cohere released Cohere Transcribe Arabic, an open-source speech-to-text model fine-tuned from Cohere Transcribe using Arabic speech data. The 2B parameter conformer-based encoder-decoder is optimized for production inference and supports regional dialects.

AI-assisted summary · qwen3.8-27bRecorded Oct 12, 2026