Speech to Text Transcription
Ins8.ai STT Engine provides powerful speech transcription for the colloquial languages and accents spoken across Asia.
We provide you the tools needed to enable Speech Recognition for your application.
Start with a single line of code -->
cURL
Python
cURL
curl –location ‘https://stt.ins8.ai/api/v1/stt/recognize?api_token=<API_TOKEN>&punctuation=True&language=en-sg×tamp=False’ \
–form ‘audio=@”{Path_to_audio_file}”‘
–form ‘audio=@”{Path_to_audio_file}”‘
Python
import requests
path = “Path_to_audio_file.wav”
def send_rest_api_request(audio_file, api_token):
response = requests.post(“https://stt.ins8.ai/api/v1/stt/recognize”,
params= {‘api_token’: api_token, ‘language’:‘en-sg’, ‘punctuation’:True, ‘timestamp’:False},
files = {‘audio’: open(audio_file, ‘rb’)}
)
return response
api_key = “<API_TOKEN>”
response = send_rest_api_request(path, api_key)
## To view the response from the terminal
print(response.json())
Check out our transcription capabilities!
Banker & Customer Interaction
JSON Response
JSON Response
{
“status”: “success”,
“metadata”: {
“sample_rate”: 16000,
“created”: 2023-06-28 05:37:45.656554,
“duration”: 97.9,
“channels”: 1,
“model”: en-sg,
},
“channels”: [
{
“alternatives”: {
“transcript”: “Hi, thank you for calling. Uh, a B. C bank, Uh, how may I help you today? Hey, hello, I’d like to check with regards to the uh, cashback credit card that I saw on your website. Okay, uh, Just before that can I know? How can I address you? My name is Mary. Okay, um, just before that, can I ask you? Uh? Are you a current credit card, Uh, holder yourself with any other cards? Uh, not with your bank. So, Um, with another bank? can I know? Um? what is the credit card you are holding right now? Okay, currently I have a Air Miles credit card with a B C bank. Okay. Um, okay, before I, uh, break down the the cashback credit card we have at our bank with you. I’ll just ask a few admin questions. if you don’t mind. Okay, sure, please go ahead. Okay, uh, if you don’t mind sharing, can I know what is your average monthly income? It’s about 45, Uh monthly. Sorry, I’m giving you annual. Monday is about 3000. Okay, and uh, what would you say would be your disposable income, Mm. Probably is about maybe. Like 30 %. Of the monthly salary. So I would say around 1.2 k. Oh, okay, is it is it around a one K? ish. Yes, I think we can set it as one K. Okay, um, can I just ask Uh, are you currently paying off any uh, car loan housing loan, et cetera using Uh, your income every month? No, not at all. Okay.”,
“sentences”: [
{
“sentence”: “Hi, thank you for calling. Uh, a B. C bank, Uh, how may I help you today?”,
“confidence”: 0.92012256,
“words”: [
{
“word”:“hi”,
“start_time”: 0.082,
“end_time”: 0.164,
“confidence”: 0.8500182,
“speaker_tag”: 2,
},
{
“word”:“thank”,
“start_time”: 0.246,
“end_time”: 0.369,
“confidence”: 0.9945379,
“speaker_tag”: 2,
},
{
“word”:“you”,
“start_time”: 0.369,
“end_time”: 0.41,
“confidence”: 0.9999546,
“speaker_tag”: 2,
},
{
“word”:“for”,
“start_time”: 0.492,
“end_time”: 0.533,
“confidence”: 0.9999973,
“speaker_tag”: 2,
},
{
“word”:“calling”,
“start_time”: 0.656,
“end_time”: 0.861,
“confidence”: 0.9999422,
“speaker_tag”: 2,
},
{
“word”:“uh”,
“start_time”: 0.902,
“end_time”: 1.066,
“confidence”: 0.3798497,
“speaker_tag”: 2,
},
{
“word”:“a”,
“start_time”: 1.189,
“end_time”: 1.23,
“confidence”: 0.9998862,
“speaker_tag”: 2,
},
{
“word”:“b”,
“start_time”: 1.353,
“end_time”: 1.394,
“confidence”: 0.9998749,
“speaker_tag”: 2,
},
{
“word”:“c”,
“start_time”: 1.476,
“end_time”: 1.517,
“confidence”: 0.9994999,
“speaker_tag”: 2,
},
{
“word”:“bank”,
“start_time”: 1.64,
“end_time”: 1.681,
“confidence”: 0.9999561,
“speaker_tag”: 2,
},
{
“word”:“uh”,
“start_time”: 1.804,
“end_time”: 2.009,
“confidence”: 0.6200119,
“speaker_tag”: 2,
},
{
“word”:“how”,
“start_time”: 2.05,
“end_time”: 2.091,
“confidence”: 0.9999485,
“speaker_tag”: 2,
},
{
“word”:“may”,
“start_time”: 2.173,
“end_time”: 2.214,
“confidence”: 0.9998251,
“speaker_tag”: 2,
},
{
“word”:“i”,
“start_time”: 2.214,
“end_time”: 2.296,
“confidence”: 0.9887221,
“speaker_tag”: 2,
},
{
“word”:“help”,
“start_time”: 2.337,
“end_time”: 2.378,
“confidence”: 0.9999102,
“speaker_tag”: 2,
},
{
“word”:“you”,
“start_time”: 2.46,
“end_time”: 2.501,
“confidence”: 0.999966,
“speaker_tag”: 2,
},
{
“word”:“today”,
“start_time”: 2.706,
“end_time”: 2.747,
“confidence”: 0.9999973,
“speaker_tag”: 2,
}
]
},
{
“sentence”: “Hey, hello, I’d like to check with regards to the uh, cashback credit card that I saw on your website.”,
“confidence”: 0.90808576,
“words”: [
{
“word”:“hey”,
“start_time”: 3.38,
“end_time”: 3.542,
“confidence”: 0.9931606,
“speaker_tag”: 1,
},
{
“word”:“hello”,
“start_time”: 3.703,
“end_time”: 3.945,
“confidence”: 0.9995745,
“speaker_tag”: 1,
},
{
“word”:“i’d”,
“start_time”: 4.43,
“end_time”: 4.551,
“confidence”: 0.2934655,
“speaker_tag”: 1,
},
{
“word”:“like”,
“start_time”: 4.591,
“end_time”: 4.631,
“confidence”: 0.9996995,
“speaker_tag”: 1,
},
{
“word”:“to”,
“start_time”: 4.752,
“end_time”: 4.793,
“confidence”: 0.9996424,
“speaker_tag”: 1,
},
{
“word”:“check”,
“start_time”: 4.914,
“end_time”: 4.954,
“confidence”: 0.9988973,
“speaker_tag”: 1,
},
{
“word”:“with”,
“start_time”: 5.116,
“end_time”: 5.156,
“confidence”: 0.9999912,
“speaker_tag”: 1,
},
{
“word”:“regards”,
“start_time”: 5.519,
“end_time”: 5.761,
“confidence”: 0.7185988,
“speaker_tag”: 1,
},
{
“word”:“to”,
“start_time”: 5.923,
“end_time”: 5.963,
“confidence”: 0.9998519,
“speaker_tag”: 1,
},
{
“word”:“the”,
“start_time”: 6.407,
“end_time”: 6.448,
“confidence”: 0.9992179,
“speaker_tag”: 1,
},
{
“word”:“uh”,
“start_time”: 6.609,
“end_time”: 6.77,
“confidence”: 0.5462188,
“speaker_tag”: 1,
},
{
“word”:“cashback”,
“start_time”: 6.811,
“end_time”: 7.255,
“confidence”: 0.70787,
“speaker_tag”: 1,
},
{
“word”:“credit”,
“start_time”: 7.335,
“end_time”: 7.376,
“confidence”: 0.9999335,
“speaker_tag”: 1,
},
{
“word”:“card”,
“start_time”: 7.699,
“end_time”: 7.82,
“confidence”: 0.9997816,
“speaker_tag”: 2,
},
{
“word”:“that”,
“start_time”: 8.022,
“end_time”: 8.062,
“confidence”: 0.9996238,
“speaker_tag”: 1,
},
{
“word”:“i”,
“start_time”: 8.264,
“end_time”: 8.304,
“confidence”: 0.9999846,
“speaker_tag”: 1,
},
{
“word”:“saw”,
“start_time”: 8.465,
“end_time”: 8.627,
“confidence”: 0.9999853,
“speaker_tag”: 1,
},
{
“word”:“on”,
“start_time”: 8.667,
“end_time”: 8.708,
“confidence”: 0.9999853,
“speaker_tag”: 1,
},
{
“word”:“your”,
“start_time”: 8.829,
“end_time”: 8.869,
“confidence”: 0.9984743,
“speaker_tag”: 1,
},
{
“word”:“website”,
“start_time”: 8.99,
“end_time”: 9.273,
“confidence”: 0.5874528,
“speaker_tag”: 1,
}
]
},
{
.
.
.
Response will be displayed here