Rediscovering a technique to shoot 10 arrows in 4.9 seconds

I gave it a quick comparison to Ivona (which was the best TTS engine last I checked) and found that by pasting in the first sentence from the video, both did a relatively poor job. Ivona was more natural sounding, but still wasn't anywhere near as good as the video.

I know Ivona has a phonetic markup language, so it's possible that the reason the video sounds so good is that someone has spent a lot of time tweaking it to get rid of any mispronunciations and misplaced inflexions.