Ron Amadeo, for Ars Technica:
Duplex patiently waited for me to awkwardly stumble through my first ever table reservation while I sloppily wrote down the time and fumbled through a basic back and forth about Google’s reservation for four people at 7pm on Thursday. Today’s Google Assistant requires authoritative, direct, perfect speech in order to process a command. But Duplex handled my clumsy, distracted communication with the casual disinterest of a real person. It waited for me to write down its reservation requirements, and when I asked Duplex to repeat things I didn’t catch the first time (“A reservation at what time?”), it did so without incident. When I told this robocaller the initial time it wanted wasn’t available, it started negotiating times; it offered an acceptable time range and asked for a reservation somewhere in that time slot. I offered seven o’clock and Google accepted.
From the human end, Duplex’s voice is absolutely stunning over the phone. It sounds real most of the time, nailing most of the prosodic features of human speech during normal talking. The bot “ums” and “uhs” when it has to recall something a human might have to think about for a minute. It gives affirmative “mmhmms” if you tell it to hold on a minute. Everything flows together smoothly, making it sound like something a generation better than the current Google Assistant voice.
So Google’s demo at I/O 2018 was partly staged. The journalists invited to test it out were not able to speak directly to Google Assistant but had to have an engineer enter their data manually. I assume that that last integration will be one of the easier parts of the project, which as a whole is extremely impressive. It will need to me more accurate though, so Google won’t need people to oversee the calls themselves — Google says it currently handles 8 out of 10 calls without the need for human intervention.
Other reports about Google Duplex from the past day or so: