Google patents system to make AI audio sound more human-like
Google describes a method for creating audio that sounds more natural by using two different computer models. The first model creates a basic script from data, while a second, faster model rewrites it to add human-like speech patterns and remove robotic tones.
In the filing’s own words
Provided are computer systems and methods for automatic generation of natural-sounding audio content from a variety of input data. The proposed systems and methods address several technical challenges observed in previous attempts to apply machine learning to this task. In particular, when applied to the task of automatic audio content generation, traditional large models such as large language models (LLMs) or similar often produced audio content that sounded unnatural due to issues such as preachy tones, excessive flattery, awkward transitions, monotone delivery, and/or limited conversation length. These drawbacks made the generated dialogues feel less engaging and realistic. Additionally, the proposed systems and methods provide for scalable personalized audio content by splitting the process of transcript generation and personalized transcript re-writing between multiple models.
What exactly they claim (claim 1)
1. A computer-implemented method for automatic generation of a revised transcript, the method comprising: obtaining, by a computing system comprising one or more computing devices, a corpus of context data; processing, by the computing system, the context data with a first machine-learned model to generate, as output of the first machine-learned model a transcript for audio content, wherein the transcript comprises description of one or more topics contained within the context data; and generating, using a second, different machine-learned model, by the computing system, the revised transcript from the transcript, wherein the revised transcript includes an increased number of linguistic characteristics indicative of human speech, and wherein the second machine-learned model comprises one or both of a smaller number of parameters and a reduced inference latency as compared to the first machine-learned model.
Facts
- Company
- Google (Google LLC)
- Official title
- Real-Time Generation of Natural-Sounding Audio Content From Context Data Using a Multi-Model Architecture
- Publication number
- US20260279336A1
- Application number
- 19563803
- Filed
- Mar 11, 2026
- Published
- Sep 17, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G10L 13/10 Physics & computingG10L 13/04 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.