Audio Recognition

[CAPTCHAFORUM]

We provide a speech recognition method that allows you to convert an audio record to text. The method can be used to bypass audio captchas or to recognize any audio record. The limitations are:

• Max file size: 1 MB
• Audio duration: not limited
• Supported audio format: mp3 only
• Supported speech languages: English, French, German, Greek, Portuguese, Russian

The recognition is fully automated and performed by a neural network trained for speech recognition.

As we're currenly testing the audio recognition, you can get 1000 recognition requests per day for free adding an additional parameter sandbox=1 to your request.

To recognize an audio you need to:

• Encode the mp3 file to base64
• Submit a request to our API with the base64 string and the language parameter

Request body example:

{    "key":"1abc234de56fab7c89012d34e56fa7b8",
"method":"audio",
"body":"",
"lang":"pt",
"json":1
}

If everything is OK you will receive the response with your request ID {"status":1,"request":"2122988149"} or an error code if your request was incorrect.
Make a 15-20 seconds timeout then submit a HTTP GET request to our API URL: http://2captcha.com/res.php to get the result.
The full list of parameters is in the table below.

If audio is already recognized server will return the text in the following format:

{
    "status": 1,
    "request": "hello world"
}

If the recognition process is not finished yet server will return CAPCHA_NOT_READY result. Repeat your request in 5 seconds.
If something went wrong server will return an error code.

Use the recognition result the way you need it.

List of request parameters for http://2captcha.com/in.php



List of request parameters for http://2captcha.com/res.php


Request URL example:
http://2captcha.com/res.php?key=1abc234de56fab7c89012d34e56fa7b8&action=get&id=2122988149