A September 3, 2026 publication announces a streaming speech recognition model combining transcription and diarization. The text provides no performance metrics or details.
A publication dated September 3, 2026 announces the launch of VibeVoice ASR Streaming. According to the text, it is a streaming model that provides transcription and diarization—identifying who speaks in each segment—in a single model. The publication does not give metrics, supported languages, or evaluation conditions.
Engineers assessing speech recognition can consult the original announcement to check its stated scope and features; before drawing conclusions, they should verify any associated technical documentation and evaluation results. If using AI to study or apply the material, avoid submitting sensitive recordings or documents without authorization and appropriate controls.