Voxtralon your own GPUs.

Voxtral transcribes calls, meetings and voice notes on GPUs you control. The audio never leaves your network.

Start the $4,900 pilot Compare all models

4.4B

LLM_Deploy

Card no. LD-181Issued 2026-10-27Mistral AI

Voxtral Mini 4B Realtime

Pilot $4,900 fixed

Sizes: 4.4B
Active params: All parameters (dense)
Context: streaming
Licence: Apache 2.0
Fits on: CPU only at 4-bit, any GPU
Endpoint: llm.yourcompany.internal/v1
Egress: 0
Owner: YOU

The 72-hour pilot with Voxtral.

$4,900 fixed. One model, 4.4B parameters: an estimated 5.3 GB at FP8, so it fits on CPU only at 4-bit.

Live on your data

72 h$4,900 fixed

Voxtral live on your data in 72 hours. The clock starts after access and prerequisites.

Your endpoint

/v1OpenAI-compatible

OpenAI-compatible endpoint. Your applications switch by changing the base URL.

Your hardware

CPU only at 4-bit, any GPU

The readout

Evalon your data

Reference evaluation on your data. Readout and production scoping.

We size the hardware and source it at cost, with no markup. Ballpark: one H100 80GB ≈ $25–30k; a 4×H100 node ≈ $180–240k; smaller models run on far less.

Same SDK. Change the base URL.

The model is one parameter. Everything else in your application stays as it is.

client = OpenAI(
    base_url="https://llm.yourcompany.internal/v1",   # inside your network
    api_key="your-key",
)
text = client.audio.transcriptions.create(
    model="voxtral-mini-4b-realtime",
    file=open("call-2026-10-27.wav", "rb"),
)