On demand interactive content generation in audiobooks through a natural language interface
Inventors
Tsui, Kin Wai • Chang, Yuchia • Chen, Junhan
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12762323-B2
Publication Date
2026-10-13
Expiration Date
Abstract
Disclosed are systems, methods, and computer-readable media for generating interactive content of audiobooks through a natural language interface. The disclosed technology generates a system prompt based on a combination of a user prompt and personal information of the user or of the user's environment. This combination can then be input into a multimodal machine learning model or multiple unimodal machine learning models to create both text and image outputs corresponding to the requested story line. The story can then be presented to the user and edited as needed, in some embodiments using the same content generation service that produced the system prompt to begin with.
Core Innovation
The partial content describes generating a narrative with corresponding visuals from a user-provided prompt that includes a narrative seed. A virtual assistant bot combines the user-provided prompt with a system prompt and sends the resulting narrative generation prompt to a generative content generation service, which generates narrative text and corresponding visual media prompts and visuals.
A story application receives the narrative text and visuals, synchronizes them, and presents the story as a series of segments. The described interaction can include personalized story style, text-to-speech narration, additional user details, and story revision during presentation. The background section is not included in the provided partial content, so the problem being solved is not explicitly described.
Claims Coverage
The claims recite three inventive features across three independent claims covering a method, a system, and a non-transitory computer-readable storage medium.
Generating a narrative with corresponding visuals from a user prompt
Independent claim 1 covers receiving a user-provided prompt with a narrative seed, generating a narrative generation prompt from a system prompt and the user-provided prompt, and using a generative content generation service to generate narrative text and corresponding visuals. A story application synchronizes the visuals with the narrative text and presents the story as a series of segments.
System for generating a narrative with corresponding visuals
Independent claim 8 covers processors and a computer-readable storage medium containing instructions for receiving a user-provided prompt with a narrative seed, generating a narrative generation prompt, and obtaining narrative text and corresponding visuals from a generative content generation service. The story application synchronizes the visuals with the narrative text and presents the story as a series of segments.
Computer-readable storage medium for generating a narrative with corresponding visuals
Independent claim 15 covers a non-transitory computer-readable storage medium containing instructions that cause processors to combine a system prompt and a user-provided prompt, generate narrative text and corresponding visuals through a generative content generation service, synchronize the visuals with the narrative text, and present the story as a series of segments.
The three independent claims cover the same narrative-and-visual generation workflow in method, system, and computer-readable storage medium forms.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Generating interactive, personalized stories and audiobooks, including segmented stories with synchronized visuals and text-to-speech narration.
Interested in licensing this patent?