Does Voxtral Mini Transcribe Realtime 2602 support zero data retention?

Not self-serve on Pay-as-you-go. Zero data retention for Voxtral Mini Transcribe Realtime 2602 is available on request via Opper Enterprise — contact hello@opper.ai.

Where is Voxtral Mini Transcribe Realtime 2602 hosted?

Voxtral Mini Transcribe Realtime 2602 runs on EU hosting routes through the Opper gateway, with contractually enforced residency on supported providers.

Is Voxtral Mini Transcribe Realtime 2602 trained on prompts and outputs?

No. Every hosting route for Voxtral Mini Transcribe Realtime 2602 is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Voxtral Mini Transcribe Realtime 2602?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Voxtral Mini Transcribe Realtime 2602. Contact hello@opper.ai to receive it.

Voxtral Mini Transcribe Realtime 2602

by Mistral

Voxtral Mini Transcribe Realtime 2602 is a 4B streaming speech-to-text model purpose-built for live transcription. Its streaming architecture transcribes audio as it arrives, enabling responsive voice agents and real-time applications without the wait of batch processing. Natively multilingual across 13 languages, the model performs across English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch. It adds speaker diarization for multi-party transcription, context biasing for domain-specific vocabulary, and word-level timestamps for subtitle generation and content alignment, holding a 1-2% word error rate at low streaming delays. Released under Apache 2.0, Voxtral Realtime runs efficiently on edge devices and is built for voice-first applications such as live call transcription, live subtitling, real-time call analysis, and conversational AI that needs fast, accurate transcription with speaker attribution.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

33K

Max output

—

Input price

$0.04 /1M

Output price

$0.04 /1M

EU residency available
Zero data retention via Enterprise
No training by default
GDPR DPA available

Available routes

Voxtral Mini Transcribe Realtime 2602 runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
Mistral	EU	Enterprise	No	$0.04	$0.04

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Voxtral Mini Transcribe Realtime 2602 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Mistral — France🇫🇷

Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.

Zero data retention: Available via Opper Enterprise contract.
Training: No training on customer data.
Logging: Abuse monitoring (30-day retention)
Third-party access: Provider may share with subprocessors / partners
GDPR DPA: DPA available
Transfer mechanism: Not applicable — data stays in EU

Get started

Call Voxtral Mini Transcribe Realtime 2602 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "mistral/voxtral-mini-realtime-2602",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);