Mistral has introduced the Voxtral 3 voice agent SDK and a related model suite aimed at building end-to-end, real-time conversational voice agents. The package includes Voxtral Small Transcribe 3, a speech-to-text model that supports more than 50 languages, and Voxtral Mini TTS 3, a text-to-speech model that can adjust emotion, speaking pace, and emphasis based on conversational context. Mistral said Voxtral 3 combines listening, reasoning, tool calling, and speaking in a single real-time streaming pipeline, allowing deeper integration with business systems for multi-step tasks. The product is available through Mistral’s EU-hosted API and can also be deployed on a company’s own infrastructure to help preserve data sovereignty.
Mistral has released the Voxtral 3 voice agent SDK and model suite, targeting end-to-end, real-time conversational voice agents.
The package includes Voxtral Small Transcribe 3, a speech-to-text model that supports more than 50 languages. It also includes Voxtral Mini TTS 3, a text-to-speech model that can adjust emotion, speaking pace, and emphasis based on the context of a conversation.
According to the announcement, Voxtral 3 brings listening, reasoning, tool calling, and speaking into a single real-time streaming pipeline. It also supports deep integration with business systems to complete multi-step tasks.
For access, the product is available through Mistral’s EU-hosted API. It can also be deployed on a company’s own infrastructure to help ensure data sovereignty.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.