This blog post from Speechmatics explores the inherent trade-off between speed and accuracy in real-time automatic speech recognition (ASR). The authors examine the sources of latency in ASR systems, focusing on the crucial role of contextual information in achieving accurate transcriptions. They introduce a new metric for measuring real-time accuracy, considering both latency and word error rate. A comparison with competitor ASR systems highlights Speechmatics' superior accuracy at low latencies. Finally, the post discusses future directions, emphasizing the importance of incorporating non-verbal cues to further improve the speed and accuracy of real-time transcription.