STT Additional Features

When calling the STT API, you can use additional features by entering them in json format in the transcribe_options argument.
For how to call the API, please refer to the API Request page.

Korean Token Suppression Feature (suppress_korean)

Theta One STT basically performs code-switching predictions with mixed Korean and English.
(Example: I love 김밥.)

However, if you want Korean words to be written in English instead of Hangul, please set the suppress_korean option to true.

cURL

curl -X 'POST' \
  'https://stt.thetaone-ai.com/transcribe' \
  -H 'accept: application/json' \
  -H 'x-api-key: YOUR_API_KEY' \
  -H 'Content-Type: multipart/form-data' \
  -F 'file=@audio.wav;type=audio/wav' \
  -F 'transcribe_options={"suppress_korean": true}'

Python

import requests
import json

url = "https://stt.thetaone-ai.com/transcribe"
headers = {
    "x-api-key": "YOUR_API_KEY"
}

with open("audio.wav", "rb") as audio_file:
    files = {"file": ("audio.wav", audio_file, "audio/wav")}
    data = {"transcribe_options": json.dumps({"suppress_korean": True})}
    response = requests.post(url, headers=headers, files=files, data=data)

result = response.json()
print(f"Transcription: {result['text']}")

All prediction results will be written in English.
(Example: I love Gimbap.)