Cohere · voice model

Cohere Transcribe

Cohere Transcribe is a Cohere voice model released Mar 26, 2026; Cohere's newest voice model in our dataset is Cohere Transcribe Arabic. Cohere's first transcription model, an audio-in, text-out speech recognition model released Mar 26, 2026. Verified against vendor sources on Oct 26, 2026.

Reported Last verified Oct 26, 2026 · All models · JSON · Markdown

ReleasedMar 26, 2026

InAudioOutText

Key facts

Cohere Transcribe: key facts with sources
Fact	Value	Source
Vendor	Cohere	n/a
Released	Mar 26, 2026	source
Status	generally available	n/a
API id	cohere-transcribe-03-2026	source
Input	audio	source
Output	text	source

Where Cohere Transcribe sits in our data

Released Mar 26, 2026 (week 13 of 2026), in March 2026. Other models in our data released that month: Gemma 4, Voxtral TTS, GPT-5.4 mini, Mistral Small 4, Grok 4.20, GPT-5.4.
Cohere tools we cover: Cohere.
All releases by date: AI model releases by month · new AI models this week.

How Cohere Transcribe differs from Cohere Transcribe Arabic

Read from the recorded facts of the two models, not from a head-to-head test. We have not run either.

Cohere Transcribe came out 103 days before Cohere Transcribe Arabic.
Facts for the other model: Cohere Transcribe Arabic.

What we tested

Nothing yet. We have not run Cohere Transcribe ourselves, so every fact on this page is Reported from the sources below. When we do test it, the scope will be stated here and in our test logs. See methodology.

Not verified, left out

We could not confirm these on a vendor page, so we do not state them.

License and price were not captured.

Sources

Cohere release notes