Speech Recognition

#voice to text

• HiVoicy Speech Recognition can detect voice and get back the text such as Phonetic and Text.
• Detect sound file types: mp3, ogg, wav, m4a and wma.

Python Quick Start

  import requests

  api_url = 'https://speech-recognition-english.p.rapidapi.com/api/asr'
  api_key = 'Your API Key'

  sound_path = 'Sound directory path'
  sound_name = 'Sound file name'

  files = {'sound': (sound_name, open(sound_path + sound_name, 'rb'), 'multipart/form-data')}
  header = {
      "x-rapidapi-host": "speech-recognition-english.p.rapidapi.com",
      "x-rapidapi-key": api_key
      }
  response = requests.post(api_url, files=files, headers=header)

####JSON output

{
  "statusCode": 200,
  "statusMessage": "OK",
  "hasError": false,
  "request": {
    "conversationID": "558ac9e361474095b3932766e12271d5",
    "linkFile": "",
    "packetID": "13e814954f804c74a1c652813013650e",
    "timeStamp": 132492249210298480,
    "userID": "b12ee63a8ae74ca990449a17e8e71fac"
  },
  "data": {
    "phonetic": "Phonetic of text",
    "text": "Your text of voice ",
    "duration": 2
  }
}