Voice Recognition and React

Hi, Please find the details below. 01) There will be a audio file in audio format. 02) User will tell a word 03) System should convert the audio in to text and find the word is in which min and take the timer of the audio player (in system or computer player) to the min the word is in. Note: Converting the audio to text should be done like convert the audio to text and note down in a way where the time of each word is also recorded, then only can take the time and go to player to take the timer to such time. Text document can be in any format as far as the time and words are recorded in a way to be easy to read the data later. The main audio file will be loaded first by a file chooser. Quarrying word will be sent by a audio listener using microphone (external or internal). Converted document from audio also should be saved. (in the same location of audio file and the same name of audio file)