Back to results
US 2026/0290308 A1Published application
System
AssigneeSoftBank Group Corp.
InventorMasaru YAHIRO
Life of this patent
Estimating the term…
Abstract
A system includes a processor that is configured to receive a delivery time, a theme, and an emotion specified by a user, generate a prompt for instructing a generative AI model to generate audio content based on the received delivery time, theme, and emotion, cause the generative AI model to generate the audio content using the prompt, and convert the generated audio content into audio data by using a speech synthesis technique and provide the audio data to the user.
Claims20
A system comprising:
- circuitry configured to:
- receive, via a communication interface coupled to a packet-switched network, user instruction information from a terminal device, the user instruction information including a delivery time, a theme, and an emotion specified by a user;
- generate a prompt sentence for instructing a generative AI model to generate audio content based on the received delivery time, theme, and emotion;
- cause the generative AI model to generate the audio content using the prompt sentence;
- and
- convert the generated audio content into audio data using a speech synthesis technique and transmit the audio data to the terminal device via the communication interface.
3 more elements
A system comprising:
- circuitry configured to:
- receive, via a communication interface coupled to a packet-switched network, user instruction information from a terminal device, the user instruction information including a delivery time, a theme, and an emotion specified by a user;
- calculate a target content length from the delivery time, collect related information from one or more information providing services via the communication interface based on the theme, and generate a prompt sentence incorporating the target content length, the theme, the emotion, and the collected related information;
- input the prompt sentence to a generative AI model and obtain program text information generated by the generative AI model, and adjust an amount of the program text information so that a playback time calculated based on an assumed speech rate matches or approximates the delivery time;
- and
- convert the adjusted program text information into audio data using a speech synthesis technique and transmit the audio data to the terminal device via the communication interface.
3 more elements
A method comprising:
- receiving, via a communication interface coupled to a packet-switched network, user instruction information from a terminal device, the user instruction information including a delivery time, a theme, and an emotion specified by a user;
- generating a prompt sentence for instructing a generative AI model to generate audio content based on the received delivery time, theme, and emotion;
- causing the generative AI model to generate the audio content using the prompt sentence;
- and
- converting the generated audio content into audio data using a speech synthesis technique and transmitting the audio data to the terminal device via the communication interface.
2 more elements
Dependencies are inferred from the claim text.