Grok Voice STT 1.0

Model release models.dev · xAI Source language: Chinese

收录发布日期:2026-09-17(社区数据库,待与官方公告核对)。能力:见模型资料;输入:audio。上下文:15,000 tokens。定位(来源描述):Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming。实际效果:暂无本站独立评测;能力参数不代表评测成绩。资料来自…

Excerpt

收录发布日期:2026-09-17(社区数据库,待与官方公告核对)。能力:见模型资料;输入:audio。上下文:15,000 tokens。定位(来源描述):Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming。实际效果:暂无本站独立评测;能力参数不代表评测成绩。资料来自…

Short excerpt from the source — open the original for the full text.

Sources

← Back to the daily brief