Voxtral Small 24B

Description

Voxtral Small is Mistral's audio-capable model built on Mistral Small 3.1 backbone with 24B parameters. Excels at speech transcription, translation, and audio understanding. Supports 32K context (~40 min audio), 8 languages, function calling from voice, and dedicated transcription mode. Outperforms Whisper large-v3 and GPT-4o mini on audio benchmarks.

Providers

Capabilities

EU-Compliant API Access

Use Voxtral Small 24B with a simple API call. OpenAI-compatible endpoint, EU data residency guaranteed.

const response = await fetch("https://api.eurouter.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": `Bearer ${process.env.EUROUTER_API_KEY}`,
  },
  body: JSON.stringify({
    model: "voxtral-small-24b",
    messages: [
      { role: "user", content: "Hello!" }
    ],
  }),
});

const data = await response.json();
console.log(data.choices[0].message.content);