ChatGPT's Advanced Speech Mode Undergoes Significant Upgrade, Sounding Even More Natural
1 day ago / Read about 0 minute
Author:小编   

Last year, OpenAI unveiled GPT-4, introducing an enhanced speech mode that leverages a sophisticated multimodal model. This mode boasts a swift response time, with the fastest response occurring within 232 milliseconds and an average of 320 milliseconds, closely mirroring human conversational speed. Additionally, it excels in producing more natural-sounding audio, capturing non-verbal nuances such as speaking pace, and effectively conveying emotions.