The demo of Text To Speech shows its ability to converts text into spoken voice output. This API is designed specifically for Vietnamese language.

Text To Speech (TTS) could be used widely for human-assisted application to help blind people or support for digital magazine.

Usage Scenarios

The Text to Speech service understands text and natural language to generate synthesized audio output complete with appropriate cadence and intonation. The synthesized audio is streamed to the client as it is being produced, using the HTTP chunked encoding.

Solution & Technologies

  • Client Side: HTML, CSS, and JavaScript.
  • WaveNet, Hidden Markov Model, Neural Network.


  • Natural and human-like voices contribute to improved customer experience.
  • Consistent brand image can be guaranteed by using a single TTS voice across multiple contact points.
  • With its ability to vocalize dynamic content it minimizes the workload of call center agents.
  • By increasing automation it accelerates customer services and reduces operational costs.
Click on the available input passages or type in a paragraph and then choose a voice to hear the result.