Release Notes

We’re pleased to announce the release of Cohere Transcribe, our first transcription model. Cohere Transcribe specializes in audio-in, text-out, automatic speech recognition (ASR).

Technical details

• Model name: cohere-transcribe-03-2026
• Input: Audio waveform
• Output: Text
• Languages covered: English, German, French, Italian, Spanish, Portuguese, Greek, Dutch, Polish, Vietnamese, Chinese, Arabic, Japanese, Korean.
• License: Apache 2.0
• API endpoint: Audio Transcriptions API

Getting started

The model is available immediately through Cohere’s Audio Transcriptions API endpoint. You can start transcribing audio using the following example query:

1
import cohere
2
3
co = cohere.ClientV2()
4
5
response = co.audio.transcriptions.create(
6
    model="cohere-transcribe-03-2026",
7
    language="en",
8
    file=open("./sample.wav", "rb"),
9
)
10
11
print(response)

Availability

You can access Cohere Transcribe via our API for free, low-setup experimentation subject to rate limits. See the Different Types of API Keys and Rate Limits page for usage details and integration guidance.

For production deployment without rate limits, provision a dedicated Model Vault. This enables low-latency, private cloud inference without having to manage infrastructure. Pricing is calculated per hour-instance, with discounted plans for longer-term commitments. Contact our team to discuss your requirements.