Mistral
Voxtral Small 24B 2507 STT
mistralai/voxtral-small-24b-2507-stt
Voxtral Small 24B 2507 STT is a speech transcription model from Mistral AI. It is suited for transcription, translation, and audio understanding workloads that benefit from its larger model capacity.
RoleTurns audio into text.
$50
In / M
Free
Out / M
—
Context
- AA intelligence index
- Not on listing
- Inputs
- audio
- Outputs
- transcription
- Tools
- Not listed
- Structured output
- Not listed
- Reasoning
- Not listed
- Weights
- Open · mistralai/Voxtral-Small-24B-2507
- Listed
- Aug 13, 2026
01 · What it's good at
Use it for this.
Three jobs this model is built for, and the ones to give to something else.
01
Interviews, calls, and voice notes
Skip it for
- Summaries. Transcribe first, then send the text to a cheap chat model.
02 · Example tasks
What you'd actually send it.
Real inputs, not a benchmark. Paste one into the snippet below to try it.
You send
Transcribe this recorded call.
Why this model
Audio in, text out.
03 · Your stack
Where it sits: Draw, speak, listen.
Transcription models listen. The transcript is the product. Summaries, speakers, and timestamps depend on the specific model.
Layer 01
Retrieve
Layer 02
Plan & reason
Layer 03
Do the volume
Layer 04
Gate & route
Layer 05 · this model
Draw, speak, listen
04 · Wire it up
One request. Paste and run.
Uses OpenRouter, so one key works for every model on this site. Set OPENROUTER_API_KEY and swap the prompt for one of the tasks above.
import { readFile } from "node:fs/promises";
const audio = (await readFile("call.m4a")).toString("base64");
const res = await fetch("https://openrouter.ai/api/v1/audio/transcriptions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "mistralai/voxtral-small-24b-2507-stt",
input_audio: { data: audio, format: "m4a" },
language: "en",
}),
});
const { text } = await res.json();
console.log(text);
05 · Watch out for
Gotchas.
This lesson is generated from the model type and the live listing. It has not been hand-reviewed yet.
Check the listing for supported parameters before you rely on tools or structured output.
Sources
Lessons are written from each model's listing and the linked docs. We don't publish our own benchmark numbers; the index above is Artificial Analysis, as shown on OpenRouter.