skip to content
gigarouter gigarouter
models / speech-to-text · coming soon

Voxtral Mini 4B Realtime 2602

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

published Jan 2026 · updated Mar 2026

Voxtral Mini 4B Realtime 2602 is a multilingual, realtime speech-transcription model that achieves accuracy comparable to offline systems with sub-500ms latency.

est. price
~$0.0034
· estimated, set at launch
API providers
0
downloads / mo
2M
license
apache-2.0

specs

TaskAutomatic Speech Recognition (ASR) / Real-Time Transcription
ArchitectureNatively streaming causal audio encoder (970M) + language model (3.4B) with sliding window attention
Parameters4B (BF16)
Languages13 languages (Arabic, German, English, Spanish, French, Hindi, Italian, Dutch, Portuguese, Chinese, Japanese, Korean, Russian)
LicenseApache 2.0

about this model

Voxtral Mini 4B Realtime 2602 is a realtime automatic speech recognition (ASR) model hosted on gigarouter that transcribes speech in 13 languages with sub-500ms latency, matching offline quality at configurable delays.

Architecture and Streaming

The model uses a custom causal audio encoder (≈970M parameters) and a language model backbone (≈3.4B parameters) built on the Delayed Streams Modeling framework with Ada RMS-Norm. Sliding window attention enables continuous streaming of arbitrary length. Transcription delay is configurable from 80ms to 2400ms; at 480ms delay the model achieves word error rates on par with leading offline open-source systems and realtime APIs, including Whisper.

Architecture diagram of Voxtral Realtime showing causal audio encoder and language model with sliding window attention

Benchmark Results

On the Fleurs dataset (13 languages), the model at 480ms delay achieves an average WER of 8.72%, compared to 5.90% for the offline Voxtral Mini Transcribe 2.0. Language-specific results:

ModelDelayAVGArabicGermanEnglishSpanishFrenchHindiItalianDutchPortugueseChineseJapaneseKoreanRussian
Voxtral Mini Transcribe 2.0Offline5.90%13.54%3.54%3.32%2.63%4.32%10.33%2.17%4.78%3.56%7.30%4.14%12.29%4.75%
Voxtral Mini 4B Realtime 2602480ms8.72%22.53%6.19%4.90%3.31%6.42%12.88%3.27%7.07%5.03%10.45%9.59%15.74%6.02%

On long-form English benchmarks (Meanwhile, E-21, E-22, TEDLIUM), the model at 480ms produces WERs of 5.05%, 10.23%, 12.30%, and 3.17% respectively—within 0.3–1% of the offline model. Short-form English results (CHiME-4, GigaSpeech, AMI IHM, SwitchBoard) also remain within 0.5% of offline performance.

For further details, see the technical report, blog post, and interactive demo.

The model is released under Apache-2.0 license and runs in BF16. Throughput exceeds 12.5 tokens/second on a single GPU with ≥16GB memory.

best for

FAQ

What is the typical latency of Voxtral Mini 4B Realtime 2602?

It achieves sub-500ms realtime transcription, with configurable delays from 80ms to 2.4s. A 480ms delay is recommended as the sweet spot for accuracy and latency.

How does it compare to Whisper?

At a 480ms delay, it matches the performance of Whisper, the leading offline transcription system, while operating in realtime.

What languages does it support?

It supports 13 languages: Arabic, German, English, Spanish, French, Hindi, Italian, Dutch, Portuguese, Chinese, Japanese, Korean, and Russian.

What is the license?

Apache 2.0, allowing both research and commercial use.

How can I use this model via the gigarouter API?

Use the gigarouter OpenAI-compatible endpoint with an API key, sending audio via WebSocket for realtime streaming transcription.

not yet live

We're benchmarking and onboarding Voxtral Mini 4B Realtime 2602 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.

related speech-to-text models

compare all →