Today the US Patent & Trademark Office published a patent application from Apple that relates to personalized voices for text messaging. This isn't about sending a voice recording within a text message, it's about using a new voice modeling system wherein someone receiving your text message won't have to read it but rather hear it in the senders original voice.
Text communication between users of electronic devices has become an integral part of society, especially in the context of social media and instant messaging communications. However, conventional systems do not include personalization of message playback, such as personalized audio playback of received messages. These systems are also lacking with respect to user customization as to how messages are played back among various message senders. Relatedly, traditional systems are not equipped to produce personalized voices for text messages based on a small amount of audio input. Accordingly, improved systems for personalized voices are desired.
Conventional techniques for delivering received message content are generally lacking in effectiveness. In particular, traditional systems do not offer personalization when delivering received messages, such as an audio read-out of a received message that is tailored to the message recipient. For example, in response to receiving a message from a contact named "John," a user may desire to listen to the message in John's voice, which enhances user experience while increasing efficiency of the device by eliminating the need for the user to read the received message.
A system for personalized voices for text messaging is provided in order to improve messaging technology, in accordance with the system and methods described in the patent. In some examples, a plurality of speech inputs is received from a first user. A voice model is obtained based on the plurality of speech inputs. A user input is received from the first user, the user input corresponding to a request to provide access to the voice model. The voice model is provided to a second electronic device. In some examples, a message is received from a respective user of a second electronic device. In response to receiving the message, a voice model of the respective user is received. Based on the voice model, an audio output corresponding to the received message is provided.
Apple's patent FIG. 8 below illustrates system #800 for operating a digital assistant, and in particular, for utilizing personalized voices for text messaging; FIG. 9, a user input is received corresponding to a request to provide access to the voice model; FIG. 10 illustrates the voice model of the first user being received at the second device associated with the second user, such as device #1000. FIG. 11 illustrates process 1100 for operating a digital assistant, and in particular, for utilizing personalized voices for text messaging.
Apple's patent application '51062 that was made public today was originally filed in late October 2022 under application number 17/973395. The lead inventor listed on the patent filing is D. Winarsky, Director, Siri Text-to-Speech.