Deploy Mistral AI’s Voxtral on Amazon SageMaker AI

Mistral AI’s Voxtral models combine text and audio processing capabilities in a single framework. The Voxtral family includes two distinct variants designed for different use cases and resource requirements. The Voxtral-Mini-3B-2507 is a compact 3-billion-parameter model optimized for efficient audio transcription and basic multimodal understanding, making it ideal for applications where speed and resource efficiency are priorities. The Voxtral-Small-24B-2507 is 24-billion-parameter model built on the Mistral Small 3 backbone that supports advanced chat capabilities, function calling directly from voice input, and complex audio-text intelligence, perfect for enterprise applications requiring nuanced understanding and multilingual audio processing. Both models support long-form audio context of up to 30–40 minutes, feature automatic language detection, and maintain a 32,000-token context length. They are released under the Apache 2.0 license, making them readily available for both commercial and research applications.

Voxtral models feature multimodal intelligence that processes spoken and written communication within ...