做语音转录或实时字幕的开发者终于有了一个开源且低延迟的选择——Voxtral Realtime 的 Apache 2 许可和 sub-200ms 延迟值得一试。
Mistral 发布了 Voxtral 2，包含两个新模型：Voxtral Realtime（实时转录，延迟可低于 200 毫秒，Apache 2 许可）和 Voxtral Mini Transcribe 2（支持说话人分离、词级时间戳和上下文偏置）。该模型支持 13 种语言，通过 Mistral API 提供，是市场上性价比最高的转录 API 之一。
Very excited to release Voxtral 2! Voxtral 2 come…
Very excited to release Voxtral 2!
Voxtral 2 comes with two powerful new models:
Voxtral Realtime: a SOTA real-time transcription model released under an Apache 2 license, with latency configurable to sub-200 ms
Voxtral Mini Transcribe 2: a SOTA transcription model with speaker diarization, word-level timestamps, and context biasing
Voxtral 2 supports 13 languages. It’s available on the Mistral API and is one of the most cost-effective transcription APIs on the market.