• A01, please have a meal 

• Please handle your business from window 001 to 03 

• This train will arrive at South Railway Station, please prepare to get off in advance 

Speech synthesis (TTS) technology, as an important technology in the field of artificial intelligence, has penetrated into the public life. By transforming text into vivid and natural speech output, it brings a lot of convenience to people's life. Based on the self-developed intelligent voice chip of Chipintelli,  Chipintelli  offline speech synthesis technology can quickly synthesize voice from text in a no-network environment, providing smooth, natural, stable and consistent synthesis experience. The technical solution has the following characteristics: 

01 Highly user-defined 

A single synthesis of text 4K bytes, that is, about 2000 Chinese characters. At the same time, support speech speed, intonation, volume adjustment, including a variety of timbre and mood, such as intellectual female voice, rich male voice, natural timbre, diversified style. There are also dozens of special ringtones, such as alarms and ticking sounds. Users can flexibly adjust according to specific requirements to meet different scenarios and user requirements. 

02 Intelligent Analysis 

With text intelligent analysis and processing function text automatic processing of common values, telephone numbers, time and date, weights and measures symbols and other formats, can achieve the correct and smooth synthesis of polyphonics, numbers, values, dates, times and letters. 

03 Flexible control 

Support a variety of control commands, including start synthesis, stop synthesis, pause synthesis, resume synthesis, status query, etc., make the speech synthesis function more flexible. Offline speech synthesis technology can be applied to story machine, queue number, traffic station (airport/train station/subway), attendance machine, customer service machine, vending machine and other fields. 

Speech synthesis technology transforms "seeing with the eyes" into "hearing with the ears", bringing a more intelligent experience to people's lives. Chipintelli  will soon launch a Chinese-English hybrid synthesis model and develop personalized speech synthesis customization. In the future, we will continue to deepen speech synthesis technology to bring users a more natural and realistic communication experience.