Voxtral Mini 3B API.
Give recordings a next step.

Voxtral Mini 3B is listed for transcription and audio understanding. Start with speech-to-text, then pass a reviewed transcript to a language model when your product needs a summary or follow-up.

€5 in free credits for every new customer.

Try Voxtral Mini 3B

From €0.000774 per audio minute. View the pricing details.

Speech to text
with Voxtral Mini 3B.

Practical starting points for Voxtral Mini 3B. Choose one task, define the expected output and measure the result on your own examples.

Turn recordings into notes

Transcribe a recording, retain the original and use the resulting text as input to your note-taking workflow.

Prepare searchable audio

Store reviewed transcripts with recording identifiers so people can find the right material through your own search layer.

Evaluate spoken questions

Explore audio-understanding workflows after confirming supported routes. Keep direct audio understanding distinct from summarizing a transcript.

Explore the speech to text workflow ↗

Voxtral Mini 3B pricing

Voxtral Mini 3B
API pricing.

These are catalogue “From” rates in EUR. Dynamic pricing can change the applicable price. Confirm your model, request route and active billing unit before estimating a workload.

See Voxtral Mini 3B on the rate card ↗

Per audio minute: From€0.000774

A concrete example
60 audio minutes = €0.046440 at the displayed starting rates.

Illustration only; excludes retries, other models and paid tools. Catalogue updated 2026-10-22.

Check current rates ↗

API integration

How to use
the Voxtral Mini 3B API.

Use the Blade model ID voxtral-mini-3b and keep your API key in your backend environment. Verify account access and supported parameters before connecting production traffic.

Create a Blade API key in the console.
Run pip install openai and set BLADE_API_KEY.
Run a small request and inspect the output before building the rest of your workflow.

Read the API reference ↗

python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.models.blade.sh/v1",
    api_key=os.environ["BLADE_API_KEY"],
    timeout=120.0,
)

with open("recording.wav", "rb") as audio:
    transcript = client.audio.transcriptions.create(
        model="voxtral-mini-3b",
        file=audio,
    )
print(transcript.text)

Install openai, set BLADE_API_KEY and provide recording.wav. The documented route accepts audio uploads up to 25 MB. This sends a billed request.

Voxtral Mini 3B API FAQ.

What can I use Voxtral Mini 3B for?

Voxtral Mini 3B is listed for transcription and audio understanding. Start with speech-to-text, then pass a reviewed transcript to a language model when your product needs a summary or follow-up. Its Blade model ID is voxtral-mini-3b.

How much does Voxtral Mini 3B cost on Blade?

Per audio minute: from €0.000774. These are dynamic catalogue starting rates as of 2026-10-22, not fixed prices for every request. Check the console for current rates.

What should I confirm before integrating?

The published transcription route accepts multipart audio files. Direct audio conversation and model-specific options need separate verification; the upstream model card does not guarantee endpoint support.

Voxtral Mini family reference; the Blade alias does not identify a dated checkpoint.

Model reference: Publisher model reference ↗. Hosted configuration and pricing: Blade catalogue, 2026-10-22.

Choose by task, input type and billing unit. Browse all models ↗

Voxtral Mini 3B API.Give recordings a next step.

Speech to textwith Voxtral Mini 3B.