Does Voxtral Mini Transcribe Realtime 2602 support zero data retention?

Not by default. See the per-route data-handling section for each route's logging stance and retention window.

Where is Voxtral Mini Transcribe Realtime 2602 hosted?

Voxtral Mini Transcribe Realtime 2602 runs on crypto rails routes through the qynio 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 no-KYC deposit available for Voxtral Mini Transcribe Realtime 2602?

Yes. A no-KYC Data Processing Agreement is available on at least one route serving Voxtral Mini Transcribe Realtime 2602. Contact hello@qyn.io to receive it.

Voxtral Mini Transcribe Realtime 2602

by Mistral

Versions:Voxtral Mini Transcribe Realtime 2602Voxtral Mini Transcribe Realtime 2602

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

onchain settlement available
No training by default
no-KYC deposit available

Available routes

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

Provider	Region	Zero data retention	Training	Input	Output
Mistral	EU	Not by default	No	$0.04	$0.04

Uptime and availability

Voxtral Mini Transcribe Realtime 2602 runs on a single route through the qynio gateway today, so its availability is that provider's availability.

100%route uptime, last 30 days

Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. .

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider qynio monitors.

Data handling per route

Each route hosting Voxtral Mini Transcribe Realtime 2602 has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.

Mistral — France🇫🇷

Zero data retention is not on by default — abuse monitoring, 30-day retention. No training on customer data. EU; deposit available.

Zero data retention: Not by default — abuse monitoring, 30-day retention. Derived from the logging and moderation facts.
Training: No training on customer data.
Logging: Abuse monitoring (30-day retention)
Moderation: Not established
Caching: Not established
Subprocessor access: Not established
no-KYC deposit: deposit available
Transfer mechanism: Not applicable — data stays in EU

Get started

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

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.QYN_API_KEY,
5  baseURL: "https://api.qyn.io/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);