Convert your voice into text


Upload file audio

Identified text :

Automated Call Center applying FPT.AI Speech


Automatic language recognition

Using the latest advanced neural network algorithms, FPT STT delivers accurate and improved audio recognition over time, recognizing linguistic variants based on regional accents, ages and the use of non-native Vietnamese words.

Automatic proper nouns transcription

STT formats specific contextual results and can correctly transcribe proper nouns (such as proper names, names of place) and appropriate language formats (such as dates and phone numbers).

Real-time or pre-recorded audio support

Audio input can be received directly from the microphone of the online application or sent from an audio file.

Automatic punctuation

Using machine learning technology, STT service automatically punctuates after each break. It is possible to add the starting and ending time of each statement, or each word being said.

Customization for every domain

In addition to the multi-purpose voice recognition service, FPT TTS provides a service channel that customize to each customer’s needs.



  • Free of charge
  • 0 – 60 minutes/month
  • No technical support


  • USD 400/month
  • 20.000 minutes/month
  • Standard Technical Support

Business Premium

  • USD 800/month
  • 50.000 minutes/month
  • Standard Technical Support

    For extra call

    50.001 – 500.000 minutes: $ 0.004/15 seconds

    500.001 – 1.000.000 minutes: $ 0.003/15 seconds

Let's experience the best Vietnamese speech recognition service