Voxtral-Small-24B-2507
Voxtral-Small-24B-2507 is an AI model published by MistralAI, released on 2025-07-15, for 语音大模型, with 240.0B parameters, and 32K tokens context length, requiring about 48.5GB storage, under the Apache 2.0 license.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Modality | Input | Output |
|---|---|---|
| Text | $0.01 | $0.3 |
| Audio | $0.004 | -- |
Voxtral-Small-24B是MistralAI开源的一款语音识别大模型,参数规模为240亿,基于Mistral Small 3.1语言模型增强开发而成。该模型在保留优秀文本理解能力的同时,整合了先进的音频输入处理技术,支持语音转录、翻译及音频内容理解等任务,适用于多语言场景下的生产级应用。
MistralAI提供定制化支持,包括:
Voxtral-Small-24B以Apache 2.0协议开源,旨在为开发者提供高性价比、可控制的语音理解解决方案,适用于从边缘设备到云端的大规模应用场景。
欢迎关注 DataLearner 官方微信,获得最新 AI 技术推送
