[Models](/models)/mistralai/Voxtral-Mini-4B-Realtime-Arabic

Apache 2.0

# Voxtral-Mini-4B-Realtime-Arabic

by mistralai

Mistral's streaming speech-to-text for Modern Standard Arabic and 15 dialects, 8.82% average CER at 480 ms delay

27likes

4.4Bparams

[HuggingFace](https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-Arabic)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`mistralai/Voxtral-Mini-4B-Realtime-Arabic`

## Deploy Voxtral-Mini-4B-Realtime-Arabic

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

Voxtral Mini 4B Realtime Arabic is a streaming speech-to-text model from Mistral AI, released in October 2026 under the Apache 2.0 license. It is fine-tuned from Voxtral Mini 4B Realtime for Modern Standard Arabic and dialects from the Maghreb, the Gulf, the Nile Valley and the Levant, and for code-switching, where a speaker moves between Arabic and another language mid-sentence. It produces text as the audio arrives.

At a transcription delay of 480 ms, the card reports an average character error rate of 8.82% across seven Arabic benchmarks, 0.91 points behind Mistral's offline Voxtral Transcribe Arabic at 7.91%. Two of the benchmarks, ISMA and Darija in the Wild, were built with Morocco's digital transition ministry, and scores use the card's own Arabic normalization. For other languages, the card points to the base model.

## Architecture

About 4.4B parameters in BF16: a causal audio encoder reading 16 kHz audio and a language decoder that emits text while audio streams in, with a configurable transcription delay. Fine-tuned from Voxtral-Mini-4B-Realtime-2602. Served through vLLM's /v1/realtime WebSocket endpoint or Transformers 5.2+ (VoxtralRealtimeForConditionalGeneration).

## Mixpeek SDK Integration

IngestRetrieve

\# Voxtral Arabic runs on your side. Transcribe each segment and store the
# text next to the audio, so a retriever can search what was said.
import requests

for seg in segments:  # e.g. {"key": "calls/2026-10-13/0412.wav", "start": 24.0, "text": transcript}
    requests.post(
        "https://api.mixpeek.com/v1/buckets/bkt\_your\_bucket/objects",
        headers={"Authorization": "Bearer API\_KEY", "X-Namespace": "ns\_your\_namespace"},
        json={"blobs": \[{"property": "audio", "type": "audio", "data": f"s3://your-bucket/{seg\['key'\]}"}\],
              "metadata": {"start": seg\["start"\], "transcript\_ar": seg\["text"\], "language": "ar"}},
    )

## Capabilities

*   Streaming transcription with a configurable delay
*   Modern Standard Arabic and 15 regional dialects
*   Arabic code-switching within one conversation
*   vLLM realtime WebSocket serving and Transformers support
*   Apache 2.0 license

## Use Cases on Mixpeek

Live captions for Arabic broadcasts and meetings

Transcribing dialect-heavy call recordings so they can be searched

Voice interfaces for Arabic speakers who mix in French or English

## Benchmarks

Dataset

Metric

Score

Source

Seven Arabic benchmarks (average)

CER

8.82%

Model card: mistralai/Voxtral-Mini-4B-Realtime-Arabic (self-reported, 480 ms delay, the card's Arabic normalization)

Same benchmarks, Voxtral Transcribe Arabic (offline)

CER

7.91%

Model card (self-reported comparison)

## Performance

Input Size16 kHz audio, streamed

Embedding Dimn/a (generates text)

GPU LatencyConfigured transcription delay of 480 ms in the card's evaluations

GPU ThroughputBatch dependent

GPU MemoryModel dependent

Scores use normalization co-developed with Morocco's MTNRA, covering dialect spelling, clitics, loanwords and spoken numbers; the card says scores may differ under other normalization. We have not measured it.

## Common Pipeline Companions

[

mistralai/Voxtral-Mini-4B-Realtime-2602

The base model, for languages other than Arabic

](/model/mistralai/Voxtral-Mini-4B-Realtime-2602)[

pyannote/speaker-diarization-3.1

Splits a recording by speaker before transcription

](/model/pyannote/speaker-diarization-3.1)

## Frequently Asked Questions

### What is Voxtral Mini 4B Realtime Arabic?

An open streaming speech-to-text model from Mistral AI for Modern Standard Arabic and regional dialects. It is a 4.4B-parameter fine-tune of Voxtral Mini 4B Realtime, released under Apache 2.0.

### Which Arabic dialects does it cover?

The card lists Modern Standard Arabic plus Moroccan, Libyan, Tunisian, Algerian, Hassaniya, Gulf, Najdi, Omani, Sanaani, Egyptian, Sudanese, Mesopotamian, South Levantine, North Levantine and Chadian Arabic.

### How accurate is it?

The card reports an 8.82% average character error rate across seven Arabic benchmarks at a 480 ms delay, against 7.91% for Mistral's offline Voxtral Transcribe Arabic. The scores use the card's own Arabic normalization, so test on your own recordings.

### Can it transcribe English or French?

It handles Arabic speakers switching into other languages mid-conversation. For audio that is mainly in another language, the card recommends the original Voxtral Mini 4B Realtime.

## Explore on Mixpeek

[

Browse all models

Search the full model catalog

](/models)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

Organizationmistralai

Retriever\-

Parameters4.4B

LicenseApache 2.0

Downloads/moN/A

Likes27

[

### Research Paper

Voxtral Mini 4B Realtime Arabic model card

arxiv.org](https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-Arabic)

### Build a pipeline with Voxtral-Mini-4B-Realtime-Arabic

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)