Advanced TTS to provide a variety of tones for you to choose from, and supports functions such as adjusting the speed, intonation, pause, volume, etc. Mainly used in scenarios such as e-book reading and audio message notification

Featured Functions

  • Adjustable Timbre

    Support a variety of parameter configurations, and can flexibly set the speaker's speech speed, pitch, and volume according to the scene to meet individual needs

  • Multiple Tones

    Provide 8 types of speakers, including basic sound banks and high-quality sound banks, suitable for various Solutions for Your Business such as smart hardware, news broadcasts, children's story machines, and smart customer service

  • Exclusive Hot Words

    Proper nouns can be synthesized into other pronouns according to the process language requirements of the current scene to meet individual needs

  • Multi-language Support

    Support Chinese and English mixed TTS, and more languages ​​will be supported soon

Solutions for Your Business

Audio Reading

For reading apps, including novels, news, stories, etc., provide a variety of pronunciation speakers with reading functions

Order Broadcast

Applied to scenarios such as taxi-hailing software, restaurant calling, queuing software, etc., through speech synthesis to broadcast order information, allowing you to easily obtain notification information

Travel Broadcast

Suitable for scenes such as car navigation and mobile phone navigation. It provides special broadcast sounds for travel software and guides the direction of your travel

Intelligent Voice Interaction

Provide a warm voice for various smart devices such as smart homes, speakers, vehicles, and wearable devices


What are the hot words? The format of the hot word setting? Priority in effect?
Hot words are a way to support users to customize the pronunciation, pause, timbre... of the synthesized speech. The format of the hot word setting is K-V, we will replace the matched word (K) with the provided hot word (V), and the hot word (V) is written in ssml. Hot words are divided into global hot words and domain hot words. When the domain hot words conflict with the global hot words, the hot words in the field are selected
Note:When the request text is in ssml format, the priority of the request text is higher than the hot words in the field,
and the specific priority is request ssml> hot words in the field> global hot words
Loss of speech during TTS?
Speech synthesis is a segmented synthesis process. If a piece of text cannot be parsed, the speech synthesis of this piece of text will be skipped. Please make sure that the ssml of the request or hot word is written correctly, so as to avoid the loss of audio due to errors in parsing the text. In hot words and request texts some xml special characters, such as'<','>', etc., please use'<','>' and other escape characters

We will contact you as soon as possible to provide you with timely services