Model reference · open weights
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.
About
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
| Maker | mistralai |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 4.4B |
| Variants | 1 |
| Runs with | vllm |
| Based on | mistralai/Ministral-3-3B-Base-2512 |
| Released | 2026-01-21 |
| Popularity | 2.2M downloads / month |
| Likes | 955 |
| Licence | Open weights |
How it works
Variants
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.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Voxtral-Mini-4B-Realtime-2602 | 4.4B | BF16 | ~10.2 GB | ✓ | Weights ↗ |
Using it via the API
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
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗