Mistral AI releases Voxtral 3 speech models and real-time agent SDK
What happened
On October 20, Mistral AI released the Voxtral 3 speech model family, covering transcription and synthesis, along with a real-time agent SDK. The transcription model supports more than 50 languages with under 500 milliseconds of real-time latency. The synthesis model supports more than 35 languages and over 50 dialects, and adjusts emotion, pace and accent from context. The SDK combines listening, reasoning, tool calls and speech output into one real-time agent toolkit.
Written by AI from the coverage · updated 59 minutes ago
Coverage
Follow the reports to see the story from different sides.
- Mistral AIPickMistral AI launches Voxtral 3 speech models and a real-time agent SDK
Mistral AI released the Voxtral 3 family of speech transcription and synthesis models, plus a real-time agent SDK that combines listening, reasoning, tool calls and speech output. Transcription covers more than 50 languages with under 500ms latency in real time. Synthesis covers more than 35 languages and 50 dialects, adjusting emotion, pace and emphasis from context.
Heat over time
Not enough continuous observations to draw a trend yet.