Skip to main content
Models/Mistral AI/Voxtral Small Transcribe 3

Voxtral Small Transcribe 3

Mistral AI 📝 Transcription

Mistral's flagship speech-to-text, its most accurate transcription, with the language detected. Voxtral 3.

Specifications

Input modalitiesaudio
Output modalitiestext
Streaming outputNo
Unit price$0.0001 / generation

Pricing

$0.0001 / generation

Platform credit pricing — live rates on the Models page.

Use Voxtral Small Transcribe 3 on Zubnet →

More from Mistral AI

M
Mistral Large 3
Open-weight flagship. 675B MoE (41B active), multimodal with vision. Apache 2.0 licensed.
🧠 Language Model
M
Mistral Large 4
Mistral's open-weight flagship (public preview, 2026-10-06). 1.05T MoE (52B active) with a vision encoder; reasoning on demand, tools. 1M context.
🧠 Language Model
M
Mistral Small
Fast and efficient model for simple tasks. Great balance of performance and cost.
🧠 Language Model
C
Codestral
Specialized model for code generation, completion, and understanding.
🧠 Language Model