mistralai/voxtral-small-2507
Model Card
Voxtral Small is a 24B parameter speech understanding model built on Mistral Small 3.1 under Apache 2.0. It supports 30-minute transcription, 40-minute audio understanding, Q&A, summarization, and function calling from voice in 8+ languages.
Context Window
N/A
tokens
Max Output
32,768
tokens
Input Cost
$0.1
per million tokens
Output Cost
$0.3
per million tokens
API Usage Example
Add Voxtral Small to your app with just a few lines of code.
No API keys, no backend, no configuration required.
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "mistralai/voxtral-small-2507"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Get started with Puter.js
Add Voxtral Small to your app without worrying about API keys or setup.
Read the Docs View Tutorials