A patent filed by Electronic Arts describes the ability for a player to generated an in-game voice using their own voice. While the patent was filed back in 2020, it’s only just been published, and is titled simply ‘Generating speech in the voice of a player of a video game.’
A description reveals that payers “input data that represents speech content,” which is then put through a synthesiser module, a voice convertor, and a vocoder to generated dialogue based on the sample provided.
The patent mentions that previous efforts to generate speech in games typically utilise text-to-speech technology, where audio speech is generated by a synthesiser after receiving text.
However, it adds that “such approaches usually require many speech samples (e.g. hours of speech samples) in order for the synthesiser to accurately capture the voice in the synthesised speech audio,” and that the synthesiser would need to be trained again if a different voice is required.
The tech described in the patent instead “enable speech audio to be generated in the voice of a player of a video games, using speech audio provided by the player (e.g. a small amount of speech audio such as minutes of speech audio from the player), and a voice convertor.”
It’s worth remembering that patents don’t always materialise as actual products, so there’s no guarantee that this particular tech will ever see the light of day.