Speech to Text (STT)

The industry's only child speech recognition, Korean-English code-switching support, and world-class speech recognition accuracy provided by Theta One Speech AI API.
Upload an audio file (.wav, .mp3 format) containing the speech you want to recognize, and the recognized content will be output.

Prerequisites

API usage requires a valid API key and either prepaid credits or a postpaid billing contract. If you haven't prepared yet, please refer to the documents below.

• Get API Key
• Top Up Credits

API Request

You can use the STT API using the code snippets below. Replace YOUR_API_KEY with the API key you received (starting with sk-theta-), and replace audio.wav with the path to the audio file you want to recognize.

You can use additional features by including the desired feature options in transcribe_options in json string format when making a request. For a description of each additional feature, please refer to the Additional Features page.

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": false}'

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": False})}
    response = requests.post(url, headers=headers, files=files, data=data)

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

The result is provided as json in the following format:

{
  "text": "Welcome to Theta One AI!",  // Recognized text
  "text_type": "en",  // Recognized language
  "metadata": {},
  "response_time_in_sec": 0.4252029037475586  // Time spent processing the request on the server
}

text_type is provided in the form of en, ko, or codeswitched.

Error Responses

If API processing fails, json containing an error message is returned with an HTTP error code. The types of errors that may occur and how to handle them are as follows.

400 Bad Request

There is a problem with the API request. Please check if the request format is correct.

401 Unauthorized

There is a problem with API authentication. Please check if the API key is entered correctly and if the API key status is valid.

402 PAYMENT_REQUIRED

Billing-related error. Please check if the amount of credits charged is sufficient and if the payment information is valid.

429 RATE_LIMIT_EXCEEDED

This error occurs when you send a request that exceeds the allocated requests per minute limit (Request Per Minute Limit).
Theta One API limits more than 100 requests per minute to prevent server overload due to excessive requests and unintended excessive billing.

Please try again later, or contact us to increase the limit to suit your needs.

500 INTERNAL_SERVER_ERROR

This is an error that occurs on the Theta One API server side. If it occurs, please leave the error log along with the time of occurrence and the API key you used by email (support@thetaone.co) and we will help you quickly resolve it.