Based on the industry-leading deep neural network technology, it provides highly anthropomorphic, smooth and natural speech synthesis services, making your applications and equipment more personalized
19 kinds of audio libraries with various styles are available for your choice, which are suitable for application scenarios such as audio reading, news broadcast, order broadcast, intelligent hardware, etc. More special audio libraries will be launched soon
Adjustable speaking speed and tone
It supports multiple parameter configurations, and can flexibly set the voice speed, tone, and volume of the sound library according to the needs of the scene to meet personalized needs
Support polyphone annotation
The pronunciation of Chinese polyphonic characters can be defined by marking pinyin and tone, such as "the boat has passed through 10000 mountains", "the brain turns sharply"
Multiple call methods to meet the needs of multiple scenarios
Provide REST API interface and online SDK to meet the needs of mobile APP, web side, applet, hardware and other scenarios, and provide a smooth and natural synthetic experience
Product pricing
Purchase times package
Pay as you use it
Purchase concurrent stack package
Apply for using the quality sound library
Select Product
Basic sound library
Basic sound library provides basic version of Duxiaoyao, Duxiaoyu, Duxiaomei, Duyaya sound library, covering male, female and child voices, providing you with cost-effective voice synthesis servicesProduct Price Document>
100 million free credits can be obtained after enterprise certification
100 for purchase and concurrent
Cost effective choice
Purchase Options
Package purchase by times
Specifications
1 million times: 1200 yuan
term of validity
twelvemonth
Purchase quantity
individual
¥1200
Buy Now
Application scenarios
Reading and Listening
Information broadcast
Order announcement
Intelligent hardware
Reading and Listening
Reading APP using speech synthesis technology can provide users with reading functions of multiple audio libraries, release users' hands and eyes, and provide more extreme reading experience
Cooperation cases
Characteristic advantages
Support multi language and multi voice
Support Chinese, English, Chinese and English mixed reading synthesis, provide 19 kinds of sound libraries with various styles for you to choose, so that your application has personalized sound
Rich scenario applications
It supports pure online and online offline integration. In weak network environment, it can also provide stable synthetic broadcast to meet the needs of different scenarios
Convenient and fast integration
Provide REST API interface to facilitate the synthesis of devices that can initiate network requests;Android and iOS SDKs are provided, which are lightweight and convenient for quick integration of mobile phones and smart hardware
Usage
Online API interface
Provide a REST API interface based on HTTP requests to convert text into audio files that can be played
Use Now
API documentation
Online speech synthesis SDK
Android/iOS online speech synthesis SDK is provided, which is suitable for rapid integration of mobile phones and intelligent hardware devices in a stable network environment
Use Now
SDK download
common problem
How to apply for a trial of the Zhenpin sound library?
Please submit for trial use of Zhenpin Sound LibraryCooperation consulting, an account manager will communicate with you.
How many words can be synthesized by one call of short text voice synthesis?
The text submitted in POST mode does not exceed 120 GBK bytes, that is, 60 Chinese characters or alphanumeric characters. The billing method is calculated as one call within 120 GBK bytes.
Get voice AI ability immediately
Quick and easy to get started, please click below to use now
