Voxtral

Original: Research Voxtral July 15, 2025 Mistral AI

Mistral AI releases open Voxtral speech understanding models for transcription, audio Q&A, summaries, and voice-triggered actions.

Mistral AI introduces Voxtral, a speech understanding model family with 24B and 3B variants under Apache 2.0. The models support long-context transcription, audio Q&A, summarization, multilingual detection, and function calling from voice. Mistral says Voxtral is competitive across transcription and audio understanding benchmarks, with API access starting at $0.001 per minute and local downloads available on Hugging Face.

摘要由 AI 整理,以原文為準。