Endpoints

POST /transcripts

Transcribe an audio file from a given URL. The API will download the audio found at the URL and transcribe it at our crowdsourcing platform.

JSON Parameters

Parameter

Example

Required

Description

audioSrcUrl

http://foo.com/bar.mp3

Yes

URL for the audio file to be transcribed. This must be a publicly available URL or a temporarily public URL.

uuidProject

7cf22963-51d2-4369-8030-bf6df57daf8a

Yes

UUID of the audio transcription project.

speakerCount

n

No

The number of speakers in the audio. If transcribing dual channel (stereo) audio, and you know there is exactly one speaker on each channel (for example, a phone call), setting speakerCount to 2 will enable speaker labels. If unsure of speaker count, make an uppermost guess.

languageCode



en

Yes

The language code for the language used in the input media file. Can be en,  es, etc.

locale

US

Yes

Country code related to accent.

options



{"formatText": false}



{"truncatedWords": false}


{"overlpadedVoices": false}


{"nonAudible": false}


{"nonVerbal": false}



{"phoneticWriting": false}


{"interjections": false}

No

Optional parameters for manipulating the transcript.


Setting formatText to false will disable punctuation and casing.


Setting truncatedWords to false will disable annotation of truncated words. 


Setting overlapedVoices to false will disable annotation of voice overlapping.


Setting nonAudible to false will disable annotation of nonaudible speech fragments.


Setting nonVerbal to false will disable annotation of nonverbal human noises like laughs.


Setting phoneticWriting to false will disable annotation of words written according to their phonetics.


Setting interjections to false will disable transcription of Uhms and Ers. 

Example: Create a transcript and disable text formatting and truncated words annotation.

curl --request POST \     

  --url 'https://api.atext.io/v1/transcripts' \     

  --header 'Authorization: Basic AUTHORIZATION_TOKEN' \

  --header 'Content-Type: application/json'\    

  --data '

  {

    "audioSrcUrl": "AUDIO_URL",

   "projectUuid": "PROJECT_UUID",

    "speakerCount": 2,

    "languageCode": "es",

    "locale": "US",

    "options": 

    {

      "formatText": false,

      "truncatedWords": false

    }

  }'

Expected Response

{

        "uuid": "16a54748-da46-4080-b4a1-fa18a6b223cf",

        "status": "started",

        "audioSrcUrl": "AUDIO_URL",

        "language": "es",

        "locale": "US",

        "speakerCount": 2,

        "options": {

            "formatText": false,

            "truncatedWords": false

        },

        "createdAt": "2019-12-08T01:25:49.031Z"

    }

When you create a transcript, the status goes from started to processing to ready. Processing time normally takes under 24 hours.

To get the result of the transcript, pull for the transcript id with GET requests.