Voxtral-Mini-4B-Realtime for real-time speech transcription is now available in Amazon SageMaker JumpStart
News
This article announces the availability of Voxtral-Mini-4B-Realtime in Amazon SageMaker JumpStart, a multilingual real-time speech transcription model from Mistral AI.
- Enables low-latency speech-to-text applications on AWS infrastructure
- Supports multilingual transcription across 13 languages
- Features natively streaming architecture for real-time transcription
- Offers configurable transcription delays to balance latency and accuracy
- Deploy with a few clicks via SageMaker Studio or Python SDK
Voxtral-Mini-4B-Realtime expands SageMaker JumpStart's foundation model portfolio for speech applications.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
May 14
2026
2026
Three new models for speech recognition and text-to-speech are now available in Amazon SageMaker JumpStart
May 20
2026
2026
Build real-time voice applications with Amazon SageMaker AI and vLLM
May 14
2026
2026
New models for image generation and text embeddings are now available in Amazon SageMaker JumpStart
Apr 8
2025
2025
Announcing Amazon Nova Sonic, a new speech-to-speech model that brings real-time voice conversations to Amazon Bedrock
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.