AI TOOLS RADAR
All models / MISTRALAI
mistralai logo
mistralai

Mistral: Voxtral Small Transcribe 3

Source description (English)

Voxtral Small Transcribe 3 is Mistral's flagship speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization, and supports context biasing for domain-specific vocabulary. Suited...

View source on OpenRouter
Overview

Model specifications

Context
65,536 tokens
Maximum output
52,428 tokens
Architecture
audio->transcription
Tokenizer
Mistral
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Audio seconds
$0.000067
per second
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -F 'model=mistralai/voxtral-small-transcribe-3-0' \
  -F 'file=@audio.wav'
Capabilities

Input → Output

Input
audio
Output
transcription
API

Supported API parameters

Available providers

3 providers

Checked: October 20, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Mistral

Not provided
Context
66K
Maximum output
52K

Mistral

Not provided
Context
66K
Maximum output
52K

Mistral

Not provided
Context
Not provided
Maximum output
Not provided
mistralai

4 models

All models
mistralai logomistralai

Mistral: Voxtral TTS 3

Voxtral TTS 3 is Mistral's text-to-speech model. It converts text into natural-sounding speech, offers a library of preset voices, supports zero-shot voice cloning, and accepts emotion and pace tags in...

Context
4K
Input
text
Output
speech
Characters: $13 per million characters
View model details →
mistralai logomistralai

Mistral: Voxtral Mini Transcribe 3

Voxtral Mini Transcribe 3 is Mistral's compact speech-to-text model. It takes audio input and returns a transcript with timestamps and speaker diarization. It also supports context biasing for domain terms....

Context
66K
Input
audio
Output
transcription
Audio seconds: $0.000058 per second
View model details →
mistralai logomistralai

Mistral: Mistral Large 4

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...

Context
1.0M
Input
text · image
Output
text
Input: $1.36Output: $4.18per 1M tokens
View model details →
mistralai logomistralai

Mistral: 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.

Context
Not provided
Input
audio
Output
transcription
Audio seconds: $0.00005 per second
View model details →