perspectiva aiqbenchProduse AI
analiza aiqbench
Mistral AI has expanded its multimodal capabilities with Voxtral 3, introducing new speech-to-text models that achieve competitive WER scores alongside text-to-speech and a LiveKit-based voice agent SDK. This release represents a significant step in refining practical AI applications for real-time transcription and interactive voice agents, moving beyond pure generative text tasks.
1
Sursă care acoperăMarkTechPost
Mistral AI Releases Voxtral 3: Speech-to-Text, TTS and a Voice Agent SDK
MarkTechPost1 min de cititArticolul și perspectiva sunt în engleză.
Mistral AI released Voxtral 3, a family of 3 transcription models, 1 text-to-speech model and a LiveKit-based voice agent SDK. Voxtral Small Transcribe 3 scores 2.1% AA-WER, ranking #3 on Artificial Analysis. The post Mistral AI Releases Voxtral 3: Speech-to-Text, TTS and a Voice Agent SDK appeared first on MarkTechPost.
Citește articolul complet pe MarkTechPost