Quickstart

Welcome to the Atexto API! You can use our API to access Atexto API endpoints, which can create and access human tasks for audio transcription.

Step 1: Turn audio into text with humans

Run the below cURL command to request a transcript for an audio clip. The API will download and transcribe the audio at our crowdsourcing platform.

curl --request POST \     
  --url 'https://api.atext.io/v1/transcripts' \     
  --header 'Authorization: Basic AUTHORIZATION_TOKEN' \
  --header 'Content-Type: application/json'\
  --data '
    {
	"audioSrcUrl": "https://s3.amazonaws.com/atexto-production/mp3/7510.mp3",
	"projectUuid": "7cf22963-51d2-4369-8030-bf6df57daf8a"
    }'

You'll get a response with the  uuid of the transcript and the status of the transcript request (keep track of this id!):

{
  "uuid":"0a92f260-1c43-40f0-9d5f-7d7cfa3637da",
  "status":"created",
  "audioSrcUrl":"https://s3.amazonaws.com/atexto-production/mp3/7510.mp3",
  "tags":[   ],
  "createdAt":"2019-12-02T23:10:33.752Z"
}

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

To get the results, pull for the transcript  uuid with  GET requests until the status is completed (webhooks are coming soon).

Replace  0a92f260-1c43-40f0-9d5f-7d7cfa3637da in the below curl command to the id of your transcript returned in the above API call.

curl --request GET \   
  --url https://api.atext.io/v1/transcripts/0a92f260-1c43-40f0-9d5f-7d7cfa3637da \
  --header 'Authorization: Basic AUTHORIZATION_TOKEN'

The response should look like this:

{
"uuid":"5769e0e2-96cb-488d-8723-8983e19d7c15",
"results":
  {
  "transcripts":
    [
      {
       "transcript":"You know, demons on TV like that. And... And for people to expose themselves to being rejected on TV or... You know, her hum*... Humiliated by fear factor or... Um... You know."
      }
    ],
  "items":
    [
      {
      "startTime":"00:00:00",
      "endTime":"00:00:05",
      "alternatives":
        [
          {
          "content":" You know, demons on TV like that."
          }
        ],
      "type":"phrase",
      },
      {
      "startTime":"00:00:05",
      "endTime":"00:00:05",
      "alternatives":
        [
          {
          "content":"And..."
          }
        ],
      "type":"phrase",
      },
      {
      "startTime":"00:00:05",
      "endTime":"00:00:05",
      "alternatives":
        [
          {
          "content":"And for people to expose themselves to being rejected on TV or..."
          }
        ],
      "type":"phrase",
      },
      {
      "startTime":"00:00:05",
      "endTime":"00:00:05",
      "alternatives":
        [
          {
          "content":"You know, her hum*..."
          }
        ],
      "type":"phrase with truncated word",
      },
      {
      "startTime":"00:00:05",
      "endTime":"00:00:05",
      "alternatives":
        [
          {
          "content":"Humiliated by fear factor or..."
          }
        ],
      "type":"phrase",
      },
      {
      "startTime":"00:00:05",
      "endTime":"00:00:05",
      "alternatives":
        [
          {
          "content":"Um..."
          }
        ],
      "type":"phrase with non-verbal human noise (interjection)",
      },
      {
      "startTime":"00:00:05",
      "endTime":"00:00:05",
      "alternatives":
        [
          {
          "content":"You know."
          }
        ],
      "type":"phrase",
},
      ]
    },
  "status":"completed"
  }
}

That's all there is to it!

If you ever need any help or support, use the Contact Us form in the bottom right -- or send us an email to [email protected]

Did this answer your question? Thanks for the feedback There was a problem submitting your feedback. Please try again later.

Still need help? Contact Us Contact Us