Skip to content
background gradient desk

Text to speech – the technology in the AI era

October 28, 2020

Share with:

Text to speech and the fourth industrial revolution

The world is experiencing the fourth industrial revolution, along with the rapid development of Artificial Intelligence. Almost all of the most advanced technologies at this time are equipped with AI to enhance the ability to learn and become more smart, useful over time, and Text to speech technology is also one of them. 

Previously, information is conveyed through text, but it is dry and unemotional. In the past decade, text to speech technology was developed and applied in some fields. However, the lifeless voice makes receivers bored or even annoyed. 

With the integration of Speech Synthesis, Speech Recognition and Natural Language Processing (NLP) technology, Text to speech not only reads text accurately but also does it expressively, naturally by a wide range of voice with regional, gender, etc. diversity. 

Outstanding applications of Text to Speech technology

Today, some Text to speech technology applications in the service sector to bring convenience to users that can be mentioned are: 

1. Automated call center: Businesses can use virtual agents to make outbound, inbound calls to notify new information, advertisements or confirm orders. For customers in different regions, businesses can choose regional voices that are suitable to them. 

In Vietnam, text to speech technology is integrated into Virtual Agent for Call Center by FPT.AI, helping call centers to automate many basic tasks in customer service. In fact, the Consumer finance company Home Credit deployed Virtual Agent for call center of FPT.AI to make thousands of calls to remind payment due date when the number of staff is reduced because of the decree on Covid-19 social distancing at the beginning of this year. Home Credit Virtual Agent helped the business automatically make about 20.000 calls every day with a duration of 1-2 minutes and a success rate of 98%. 

Central Power Corporation (EVN CPC) also boldly transformed and applied Text to Speech technology to customer service to provide automated responses to 13 provinces in the Central region about power outages and the time to re-supply electricity through IVR.

When customers call the hotline 19001909 of EVN CPC, “AI Virtual Agent” automatically extracts data from CRM software to identify them according to registered phone numbers. As soon as they confirm information, the system automatically looks up CRM software and determines if the power outages in their addresses are accidents or scheduled incidents. 

As a result, the system creates detailed information in the form “Mr. Nguyen Van A, address…, is in the area of power cut due to problems on electric grid/scheduled work on electric grid…The expected time to re-supply electricity is …” by combining information (Text). Then it is converted to speech to “talk” to, answer customers. The whole process of Text to Speech is handled by “AI Virtual Agent” with high speed and give responses almost immediately. 

Central Power Corporation assesses that after the initial stage of implementation, most customers are satisfied because the call center provides accurate and full information that they need. FPT.AI Text to Speech helped Central Power Corporation receive and handle nearly 46.000 calls from customers in 6 months, save more than 600 million dongs. 

2. Read e-newspaper, audiobook: Many e-newspapers have applied text to speech technology to give eyes a rest. FPT.AI Text to speech

For example, the tech websites of FPT corporation – TechInsight is integrated with FPT.AI Text to Speech developed by the technology department. With many male/female voices and regional diversity, FPT.AI Text to speech brings to readers who are tech lovers exciting experience. 

3. Movie voice over, video commentary: The voice of Ban Mai from FPT.AI is especially popular among movie reviewers and voice actors. Those videos receive hundreds of thousands of likes, tens of thousands of shares and comments. In comparison with the difficult-to-hear and boring traditional voice, FPT.AI Ban Mai’s voice is as real and natural as a human voice, helping organizations quickly convert uninteresting text to captivating movie reviews, comments on social media. 

4. Programs for visually impaired people: For visually impaired people, Text to speech clearly shows all of its usefulness when applying advanced technologies to daily life. From newspapers, movie voice over to instructions on how to use the voice, all of them provide maximum support to visually impaired people. 

Text to speech technology is becoming popular and widely applied to human life. Contact FPT.AI right now to experience the best mechanical voices in the market at this time.


? Experience FPT.AI Text to Speech solution of #FPT_AI at

☎ Hotline: 0911886353

? Email: [email protected]

Related Posts

Get ahead with AI-powered technology updates!

Subscribe now to our newsletter for exclusive insights, expert analysis, and cutting-edge developments delivered straight to your inbox!