We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.

New here? See how it works A 1-minute tour of the playground, models and your API key.

Scribe v2 vs Voxtral Mini Transcribe: API price, context & features · api14

ElevenLabs: Scribe v2 vs Mistral: Voxtral Mini Transcribe

A side-by-side comparison of ElevenLabs: Scribe v2 ($0.01 / minute) and Mistral: Voxtral Mini Transcribe ($0.01 / minute) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.

Specifications

	ElevenLabs: Scribe v2	Mistral: Voxtral Mini Transcribe
Provider	ElevenLabs	Mistral
Audio	$0.01 / minute	$0.01 / minute
Context window	-	16,384
Max output	-	13,107
Input	audio	audio
Output	transcription	transcription
Tool calling
Structured output
Reasoning control
Added	Oct 7, 2026	May 15, 2026

Key differences

Mistral: Voxtral Mini Transcribe is 18% cheaper on input tokens.

In depth

ElevenLabs: Scribe v2 is a transcription model from ElevenLabs, and Mistral: Voxtral Mini Transcribe is a transcription model from Mistral. Both sit in the transcription category, meaning the job they do is the same at a high level: you send audio in, and you get a transcription out. They are made by different vendors with different backgrounds, so if you already have a relationship with one provider or a preference for how its models behave, that alone may decide the call. Otherwise the two are close enough that the practical differences matter more than the branding.

On capabilities the two are nearly identical in shape. Both accept audio as their only input modality and both produce transcription as their only output modality. Neither exposes any supported parameters, so there is no tool calling, no structured output mode and no reasoning mode to choose between them on. The one concrete difference in the data is context length: Voxtral Mini Transcribe lists a context window of 16384 tokens, while Scribe v2 lists no context length at all. That does not automatically make Voxtral the bigger context model, since the field is simply absent for Scribe v2, but it does mean Voxtral gives you a documented number to plan against. The other concrete difference is price, and here Voxtral Mini Transcribe is the cheaper of the two on input. Output pricing is not differentiated in the data, so treat the two as about the same there.

For picking between them, start with the price signal. If your workload is input heavy, meaning lots of audio going in relative to the transcription coming back, Voxtral Mini Transcribe is the cheaper option and is the natural default. If you want a documented context window to reason about how much audio you can push through in one request, Voxtral Mini Transcribe is also the one that gives you that number. Scribe v2 is the reasonable choice when you specifically want ElevenLabs handling the transcription, or when you are already routing other ElevenLabs models through the same gateway and want to keep that vendor consistent. Since neither model supports extra parameters, there is no feature gap to weigh, so the decision comes down to vendor preference and the input price difference.

Calling either model through api14 works the same way because the gateway exposes an OpenAI-compatible API. You point your client at the same endpoint, send the same request body with the audio, and only the model id changes. Use "elevenlabs/scribe-v2" to route to Scribe v2, or "mistralai/voxtral-mini-transcribe" to route to Voxtral Mini Transcribe. Everything else in your integration, the authentication, the request shape and the response handling, stays identical, so switching between them is a one line change and you can test both against your own audio without rewriting any code.

There is no case in the facts given where Scribe v2 is clearly the better pick on capability, since the two share the same modalities, the same empty parameter list and no differentiated output price. The only reason to prefer it is vendor choice or consistency with other ElevenLabs models in your stack. If neither of those applies, Voxtral Mini Transcribe is the safer default because it is cheaper on input and documents its context length.

Switch with one string

Both models use the same endpoint and request shape. Change the model value from "elevenlabs/scribe-v2" to "mistralai/voxtral-mini-transcribe" and prompts, streaming and tools keep working.

ElevenLabs: Scribe v2 details & playground →Mistral: Voxtral Mini Transcribe details & playground →

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api14.com/api/v1",
  apiKey: process.env.API14_API_KEY,
});

const result = await client.audio.transcriptions.create({
  model: "mistralai/voxtral-mini-transcribe",
  file: fs.createReadStream("audio.mp3"),
});
console.log(result.text);

ElevenLabs: Scribe v2 vs Mistral: Voxtral Mini Transcribe

Specifications

Key differences

In depth

Switch with one string

More comparisons