# US 2025/0166612 A1 · Audio generation method and system, device, and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0166612 A1
- Document ID: US20250166612A1
- Status: Published application
- Kind: A1
- Application number: 18/948,965
- Filed: 2024-11-15
- Published: 2025-05-22
- Earliest claimed: 2023-11-17
- Applicants: Beijing Zitiao Network Technology Co., Ltd.
- Inventors: Hongxu Xu; Bing Yang
- Web page: https://patentgrep.com/patent/US20250166612A1

## CPC

- G10L 13/10: Prosody rules derived from text; Stress or intonation
- G10L 2013/105: {Duration}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

The audio generation method includes: receiving first streaming text, and converting the first streaming text into first audio; receiving second streaming text located after the first streaming text, and determining a target time point during receiving of the second streaming text based on a number of characters of the received second streaming text or interval duration between receiving of adjacent characters; obtaining audio duration of the first audio after the target time point as unplayed duration of the first audio; and converting, starting from the target time point, the second streaming text into second audio within a duration range defined by the unplayed duration and playing interval duration, where the playing interval duration represents a maximum time interval between an end time point of the first audio and a start time point of the second audio.

## Claims

### Claim 1

An audio generation method, comprising:
receiving first streaming text, and converting the first streaming text into first audio;
receiving second streaming text located after the first streaming text, and determining a target time point during receiving of the second streaming text based on a number of characters of the received second streaming text or interval duration between receiving of adjacent characters;
obtaining audio duration of the first audio after the target time point as unplayed duration of the first audio; and
converting, starting from the target time point, the second streaming text into second audio within a duration range defined by the unplayed duration and playing interval duration, wherein the playing interval duration represents a maximum time interval between an end time point of the first audio and a start time point of the second audio.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the determining a target time point based on interval duration between receiving of adjacent characters comprises:
during receiving of the second streaming text, if no next character is received within preset duration since a first time point when a character is received for the last time, using the first time point as the target time point.

### Claim 3 (depends on 1)

The method according to claim 1, wherein the determining a target time point based on a number of characters of the received second streaming text comprises:
during receiving of the second streaming text, counting a number of received characters, and using, as the target time point, a second time point when the number of characters reaches a specified number.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the converting, starting from the target time point, the second streaming text into second audio within a duration range defined by the unplayed duration and playing interval duration comprises:
determining, by using the second streaming text received before the target time point as text to be converted, conversion duration required for performing audio conversion on the text to be converted;
using a sum of the unplayed duration and the playing interval duration as total duration;
using a difference between the total duration and the conversion duration as maximum waiting duration; and
converting, starting from the target time point, the text to be converted into the second audio within the maximum waiting duration.

### Claim 5 (depends on 4)

The method according to claim 4, wherein after the maximum waiting duration is obtained, the method further comprises:
comparing the maximum waiting duration with preset maximum duration, and if the maximum waiting duration is greater than the maximum duration, using the maximum duration as the maximum waiting duration; and/or
comparing the maximum waiting duration with preset minimum duration, and if the maximum waiting duration is less than the minimum duration, using the minimum duration as the maximum waiting duration.

### Claim 6 (depends on 4)

The method according to claim 4, wherein the first audio comprises k pieces of sub-audio; and the unplayed duration is determined based on the following method of:
obtaining playing duration of the first audio based on total audio duration of the k pieces of sub-audio and total lag duration between the k pieces of sub-audio;
using, as played duration of the first audio, a difference between a first time point when a character is received for the last time and a third time point when the first sub-audio is obtained through conversion; and
using a difference between the playing duration and the played duration of the first audio as the unplayed duration of the first audio,
wherein a value of k is an integer greater than or equal to 1.

### Claim 7 (depends on 6)

The method according to claim 6, wherein the total lag duration between the k pieces of sub-audio is determined based on the following method of:
using, as playing duration of the first n−1 pieces of sub-audio, a difference between a time point when nth sub-audio is obtained through conversion and the time point when the first sub-audio is obtained through conversion;
using a difference between the playing duration of the first n−1 pieces of sub-audio and total audio duration of the first n−1 pieces of sub-audio as lag duration between kth sub-audio and (k−1)th sub-audio; and
obtaining the total lag duration between the k pieces of sub-audio based on the lag duration between the nth sub-audio and (n−1)th sub-audio,
wherein a value of n ranges from 2 to k.

### Claim 8 (depends on 7)

The method according to claim 7, wherein the using a difference between the playing duration of the first n−1 pieces of sub-audio and total audio duration of the first n−1 pieces of sub-audio as lag duration between the nth sub-audio and (n−1)th sub-audio comprises:
using, if the difference between the playing duration of the first n−1 pieces of sub-audio and the total audio duration of the first n−1 pieces of sub-audio is greater than or equal to 0, the difference as the lag duration between the kth sub-audio and the (k−1)th sub-audio; or
setting, if the difference between the playing duration of the first n−1 pieces of sub-audio and the total audio duration of the first n−1 pieces of sub-audio is less than 0, the lag duration between the nth sub-audio and the (n−1)th sub-audio to 0.

### Claim 9

An electronic device, comprising:
a memory and processor;
wherein the memory is configured to store one or more computer instructions which, when executed by the processor, cause the processor to:
receive first streaming text, and convert the first streaming text into first audio;
receive second streaming text located after the first streaming text, and determine a target time point during receiving of the second streaming text based on a number of characters of the received second streaming text or interval duration between adjacent characters;
obtain unplayed duration of the first audio after the target time point; and
convert, starting from the target time point, the second streaming text into second audio within a duration range defined by the unplayed duration and playing interval duration, wherein the playing interval duration represents a maximum time interval between an end time point of the first audio and a start time point of the second audio.

### Claim 10 (depends on 9)

The device according to claim 9, wherein the instructions causing the processor to determine a target time point based on interval duration between receiving of adjacent characters comprise instructions causing the processor to:
during receiving of the second streaming text, if no next character is received within preset duration since a first time point when a character is received for the last time, use the first time point as the target time point.

### Claim 11 (depends on 9)

The device according to claim 9, wherein the instructions causing the processor to determine a target time point based on a number of characters of the received second streaming text comprise instructions causing the processor to:
during receiving of the second streaming text, count a number of received characters, and use, as the target time point, a second time point when the number of characters reaches a specified number.

### Claim 12 (depends on 10)

The device according to claim 10, wherein the instructions causing the processor to convert, starting from the target time point, the second streaming text into second audio within a duration range defined by the unplayed duration and playing interval duration comprise instructions causing the processor to:
determine, by using the second streaming text received before the target time point as text to be converted, conversion duration required for performing audio conversion on the text to be converted;
use a sum of the unplayed duration and the playing interval duration as total duration;
use a difference between the total duration and the conversion duration as maximum waiting duration; and
convert, starting from the target time point, the text to be converted into the second audio within the maximum waiting duration.

### Claim 13 (depends on 12)

The device according to claim 12, wherein after the maximum waiting duration is obtained, the instructions further causes the processor to:
compare the maximum waiting duration with preset maximum duration, and if the maximum waiting duration is greater than the maximum duration, use the maximum duration as the maximum waiting duration; and/or
compare the maximum waiting duration with preset minimum duration, and if the maximum waiting duration is less than the minimum duration, use the minimum duration as the maximum waiting duration.

### Claim 14 (depends on 12)

The device according to claim 12, wherein the first audio comprises k pieces of sub-audio; and the instructions causing the processor to determine the unplayed duration based on the following method comprise instructions causing the processor to:
obtain playing duration of the first audio based on total audio duration of the k pieces of sub-audio and total lag duration between the k pieces of sub-audio;
use, as played duration of the first audio, a difference between a first time point when a character is received for the last time and a third time point when the first sub-audio is obtained through conversion; and
use a difference between the playing duration and the played duration of the first audio as the unplayed duration of the first audio,
wherein a value of k is an integer greater than or equal to 1.

### Claim 15 (depends on 14)

The device according to claim 14, wherein the instructions causing the processor to determine the total lag duration between the k pieces of sub-audio based on the following method comprise instructions causing the processor to:
use, as playing duration of the first n−1 pieces of sub-audio, a difference between a time point when nth sub-audio is obtained through conversion and the time point when the first sub-audio is obtained through conversion;
use a difference between the playing duration of the first n−1 pieces of sub-audio and total audio duration of the first n−1 pieces of sub-audio as lag duration between kth sub-audio and (k−1)th sub-audio; and
obtain the total lag duration between the k pieces of sub-audio based on the lag duration between the nth sub-audio and (n−1)th sub-audio,
wherein a value of n ranges from 2 to k.

### Claim 16 (depends on 15)

The device according to claim 15, wherein the instructions causing the processor to use a difference between the playing duration of the first n−1 pieces of sub-audio and total audio duration of the first n−1 pieces of sub-audio as lag duration between the nth sub-audio and (n−1)th sub-audio comprise instructions causing the processor to:
use, if the difference between the playing duration of the first n−1 pieces of sub-audio and the total audio duration of the first n−1 pieces of sub-audio is greater than or equal to 0, the difference as the lag duration between the kth sub-audio and the (k−1)th sub-audio; or
set, if the difference between the playing duration of the first n−1 pieces of sub-audio and the total audio duration of the first n−1 pieces of sub-audio is less than 0, the lag duration between the nth sub-audio and the (n−1)th sub-audio to 0.

### Claim 17

A non-transitory computer-readable storage medium comprising instructions stored thereon which, when executed by a processor, cause the processor to:
receive first streaming text, and converting the first streaming text into first audio;
receive second streaming text located after the first streaming text, and determining a target time point during receiving of the second streaming text based on a number of characters of the received second streaming text or interval duration between receiving of adjacent characters;
obtain audio duration of the first audio after the target time point as unplayed duration of the first audio; and
convert, starting from the target time point, the second streaming text into second audio within a duration range defined by the unplayed duration and playing interval duration, wherein the playing interval duration represents a maximum time interval between an end time point of the first audio and a start time point of the second audio.

### Claim 18 (depends on 17)

The medium according to claim 17, wherein the instructions causing the processor to determine a target time point based on interval duration between receiving of adjacent characters comprise instructions causing the processor to:
during receiving of the second streaming text, if no next character is received within preset duration since a first time point when a character is received for the last time, use the first time point as the target time point.

### Claim 19 (depends on 18)

The medium according to claim 18, wherein the instructions causing the processor to determine a target time point based on a number of characters of the received second streaming text comprise instructions causing the processor to:
during receiving of the second streaming text, count a number of received characters, and use, as the target time point, a second time point when the number of characters reaches a specified number.

### Claim 20 (depends on 19)

The medium according to claim 19, wherein the instructions causing the processor to convert, starting from the target time point, the second streaming text into second audio within a duration range defined by the unplayed duration and playing interval duration comprise instructions causing the processor to:
determine, by using the second streaming text received before the target time point as text to be converted, conversion duration required for performing audio conversion on the text to be converted;
use a sum of the unplayed duration and the playing interval duration as total duration;
use a difference between the total duration and the conversion duration as maximum waiting duration; and
convert, starting from the target time point, the text to be converted into the second audio within the maximum waiting duration.
