Video Gamer is reader-supported. When you buy through links on our site, we may earn an affiliate commission. Prices subject to change. Learn more
If you’ve ever dreamt of hearing yourself in a video game, you may not have to wait too long to try out your voice-acting chops after EA filed a patent enabling players to voice characters in-game. According to the company’s patent filed on October 17, 2023, the method involves “inputting, into a synthesizer module, input data that represents speech content.” The speech data entered would then be identified by the system, after which it gets sent to a voice converter, into a vocoder, and, lastly, into the final product.
In addition, EA’s proposed system will also let you “train the synthesizer” by providing it with multiple voice samples, allowing you to voice characters much faster than usual. Their patent states: “The synthesizer and vocoder may be pre-trained using recordings or input from speakers for whom there are many speech samples, enabling the learning of an accurate/realistic mapping to the audio domain.”
You can also opt to train this system gradually instead of providing several speech samples simultaneously. The patent further notes: “The acoustic feature encoder and acoustic feature decoder are initially trained prior to adding a new player’s voice and are subsequently refined when the player adds their voice and provides player speech samples.”
Unfortunately, based on EA’s highly complex patent found through the USPTO website, the technology needed to make this system work may be too advanced for it to be available in the next few years. But, much like their proposed music system that changes based on a player’s mood, the industry’s future may see players getting even more involved with how a video game’s story, setting, and gameplay unfolds.