Inference APIs
Models/Transcription/Voxtral Mini 3B

Voxtral Mini 3B API

Available Cheapest

Voxtral Mini (July 2025 release) is the 3B member of Mistral's Voxtral family, built on Ministral 3B. Served as speech to text on the OpenAI-compatible transcriptions endpoint with automatic language detection across English, Spanish, French, Portuguese, Hindi, German, Dutch and Italian. Apache 2.0 weights.

Try in playground
Speech to text8 languagesAuto languageLowest price
Modality
Audio → Text
Price
$0.0013 / audio minute
Speed
0.058× real time
Model ID
mistralai/Voxtral-Mini-3B-2507

Quickstart

You need an API key to call this model. Create a free account or log in.

Set INFERENCE_API_KEY to your key from the API Keys page, then run:

curl https://api.inferenceapis.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $INFERENCE_API_KEY" \
  -F "model=mistralai/Voxtral-Mini-3B-2507" \
  -F "file=@meeting.mp3" \
  -F "response_format=verbose_json"
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.inferenceapis.com/v1",
    api_key=os.environ["INFERENCE_API_KEY"],
)
with open("meeting.mp3", "rb") as f:
    result = client.audio.transcriptions.create(
        model="mistralai/Voxtral-Mini-3B-2507",
        file=f,
        response_format="verbose_json",
    )
print(result.text)
import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferenceapis.com/v1",
  apiKey: process.env.INFERENCE_API_KEY,
});
const result = await client.audio.transcriptions.create({
  model: "mistralai/Voxtral-Mini-3B-2507",
  file: fs.createReadStream("meeting.mp3"),
  response_format: "verbose_json",
});
console.log(result.text);

When to use it

A good fit when
  • Cheap, fast multilingual transcription in Voxtral's eight languages
  • Batch jobs where cost per minute matters most
Look elsewhere when
  • Difficult audio: Voxtral Small or Whisper are more accurate
  • Timestamps, subtitles or diarization

What it costs in practice

WorkloadCost
1 hour of audio$0.08
100 hours of audio$7.80
1,000 hours of audio$78.00

Computed from the live rate below. There is no subscription or minimum; new accounts start with free credit.

Endpoint

POST https://api.inferenceapis.com/v1/audio/transcriptions
Headers Authorization: Bearer $INFERENCE_API_KEY
Content-Type: multipart/form-data
Compatible OpenAI wire format. /openai/v1/… is accepted too, so Groq-style base URLs work with only the host changed.

Model IDs and aliases

Send any of these as model; they all resolve to this model and bill at its rate.

IDNote
mistralai/Voxtral-Mini-3B-2507Canonical
voxtral-miniAlias
voxtral-mini-3bAlias

Request body

ParameterTypeDescription
model required string Model ID: mistralai/Voxtral-Mini-3B-2507 — also accepted: voxtral-mini, voxtral-mini-3b
file required file The audio file (multipart/form-data): mp3, mp4, m4a, wav, webm, flac, ogg. Up to 100 MB.
language string ISO-639-1 language code, e.g. en. Improves accuracy and latency when known.
prompt string Optional text to guide style or spelling of names and terms.
response_format string json (default), verbose_json, text, srt or vtt.
timestamp_granularities array ["segment"] and/or ["word"] with verbose_json.
temperature number Sampling temperature between 0 and 1.

Response

200 OK · application/json
{
  "language": "en",
  "duration": 12.4,
  "text": "Thanks everyone for joining. Let's start with the roadmap.",
  "segments": [
    { "id": 0, "start": 0.0, "end": 3.1, "text": "Thanks everyone for joining." },
    { "id": 1, "start": 3.1, "end": 6.0, "text": "Let's start with the roadmap." }
  ]
}

Pricing

Price$0.0013 / audio minute
BillingPay as you go from prepaid credits. No subscription, no daily request or token cap. See all pricing.

Notes

  • Billing is per minute of audio, measured from the uploaded file.
  • Text only: verbose_json adds the duration but no timestamps or language field; srt/vtt return a 400 pointing you to Whisper or Parakeet.

Compare Voxtral Mini 3B with…

Whisper Large v3Parakeet TDT 0.6B v3Voxtral Small 24BOpenAI Whisper (whisper-1)Whisper Large v3 Turbo on GroqDeepgram Nova-3AssemblyAI Universal

Languages

Per-language codes, tips and quickstarts: speech-to-text languages.

Questions about Voxtral Mini 3B

Which languages does it support?

The same eight as Voxtral Small: English, Spanish, French, Portuguese, Hindi, German, Dutch and Italian, with automatic detection.

Mini or Small?

Mini is a third of the price and a fraction of the size. For clean audio the difference is small; for accents, noise and crosstalk Small is the safer choice. Both were measured on the same 2-second clip at 0.3 to 0.4 s here.

Does it return timestamps?

No. Transcript and duration only; for timestamps or subtitles use Whisper or Parakeet.

Licence

Voxtral Mini 3B is published by Mistral AI under the Apache 2.0. Your use of its output is also subject to that licence.

Errors

Errors use the OpenAI envelope: {"error": {"message", "type", "code"}}. 401 missing or invalid key · 402 insufficient_balance · 404 model_not_found · 503 model_unavailable · 502 backend error, safe to retry. Full table with what to retry: API documentation. Errors from other providers: provider error reference.