Model reference · open weights

Voxtral-Mini-Realtime-2602

Voxtral-Mini-Realtime-2602 is an open-weight audio or speech model from mistralai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Audio mistralai 1 variants 2.2M downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What Voxtral-Mini-Realtime-2602 is

Voxtral Mini 4B Realtime 2602 Voxtral Mini 4B Realtime 2602 is a multilingual, realtime speech-transcription model and among the first open-source solutions to achieve accuracy comparable to offline systems with a delay of <500ms. It supports 13 languages and outperforms existing open-source baselines across a range of tasks, making it ideal for applications like voice assistants and live subtitling. Built with a natively streaming architecture and a custom causal audio encoder - it allows configurable transcription delays (240ms to 2.4s), enabling users to balance latency and accuracy based on their needs. At a 480ms delay, it matches the performance of leading offline open-source transcription models, as well as realtime APIs. As a 4B-parameter model, is optimized for on-device deployment, requiring minimal hardware resources. It runs in realtime with on devices minimal hardware with throughput exceeding 12.5 tokens/second. This model is released in BF16 under the Apache-2 license, ensuring flexibility for both research and commercial use. For more details, see our: - Blog post - Demo - Technical report - vLLM's blog on streaming input Key Features Voxtral Mini 4B Realtime consists of two main architectural components: - ≈3.4B Language Model - ≈970M Audio Encoder - The audio encoder was trained from scratch with causal attention enabling streaming capability - Both the audio encoder as well as the LLM backbone use sliding window attention allowing for "infinite" streaming - For more details, refer to the technical report The Voxtral Mini 4B Realtime model offers the following capabilities: - High-Quality Transcription: Transcribe audio to text with confidence. - Multilingual: Supports dozens of languages, making it perfect for multilingual transcription tasks. - Real-Time: Fast streaming ASR model, enabling real-time transcription use cases. - Configurable Transcription Delays: Customize the transcription delay to balance quality and latency, from 80ms to 2.4s. Use Cases Real-Time Transcription Purposes: - Private meeting transcriptions - Live subtitle creation - Real-time assistants with speech understanding - And more Bringing real-time transcription capabil

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makermistralai
TypeAudio & music
Parameters (lead)4.4B
Variants1
Runs withvllm
Based onmistralai/Ministral-3-3B-Base-2512
Released2026-01-21
Popularity2.2M downloads / month
Likes955
LicenceOpen weights

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
Voxtral-Mini-4B-Realtime-26024.4BBF16~10.2 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys voxtral-mini-realtime-2602 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (voxtral-mini-realtime-2602 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="voxtral-mini-realtime-2602" -F file=@audio.mp3

Details

Languages, data & research

Languages

en fr es de ru zh ja it pt nl ar hi ko

Tags

vllm safetensors voxtral_realtime mistral-common automatic-speech-recognition en fr es de ru zh ja it pt

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want Voxtral-Mini-Realtime-2602 on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms