V-Blaze and V-Cloud Online Help

Basic Workflow

The basic workflow for V‑Cloud API includes two steps.

  1. Submit audio with transcription parameters via a form-field POST request to the /transcribe endpoint. A requestid string is returned for tracking purposes.

  2. Retrieve the transcript with the returned requestid from the /transcribe/result endpoint.

Note

202 No result is currently available will return until the transcription process is complete.

Transcription Request

Run the following commands to submit a transcription request to the V‑Cloud API.

Set variables with a valid V‑Cloud token and an audio file to transcribe:
token=your-token-here
file=/path/to/audioSample.wav
Submit transcription request with the cURL utility:
response=$(curl -s -F "file=@$file;type=audio/x-wav" -F "token=$token" -F "model=eng-us:callcenter" -F "emotion=true" -F "gender=true" -X POST https://vcloud.vocitec.com/transcribe) && echo $response && requestid=$(echo $response | cut -d\" -f4)
Fetch Transcription Results
Command to get download link for results:
curl -sL "https://vcloud.vocitec.com/transcribe/result/$requestid?token=$token"

The V‑Cloud API is accessible to any programming language capable of performing HTTP POST and GET calls. The following links contain V‑Cloud request samples in various programming languages:

Sample Transcripts

JSON is the default output format for transcripts. For more information on different output formats, refer to output. The following sample is an unaltered JSON transcript.

{"started":"2020-04-03 14:28:59.457194","asr":"6.1.0-b1","donedate":"2020-04-03 14:29:22.975662","nchannels":1,"recvtz":["EDT",-14400],"streamtags":{"model":"eng-us:callcenter"},"ended":"2020-04-03 14:29:22.976576","confidence":0.88,"utterances":[{"confidence":0.88,"end":1.34,"recvtz":["EDT",-14400],"start":0.05,"donedate":"2020-04-03 14:29:22.975662","recvdate":"2020-04-03 14:28:59.488266","events":[{"confidence":0.98,"end":0.41,"start":0.05,"word":"Hello"},{"confidence":0.84,"end":1.34,"start":0.5,"word":"earthlings."}],"metadata":{"source":"Hello_Earthlings.wav","model":"eng-us:callcenter","uttid":0,"channel":0}}],"source":"Hello_Earthlings.wav","audiosecs":1.43,"model":"eng-us:callcenter","recvdate":"2020-04-03 14:28:59.488266"}

Optional — Make the JSON transcript easy to read by using the pipe operator to redirect transcript results to Python's json.tool module:

curl -sL "https://vcloud.vocitec.com/transcribe/result/$requestid?token=$token" | python -m json.tool

The result is a readable JSON transcript:

{
  "started": "2020-04-03 14:28:59.457194",
  "asr": "6.1.0-b1",
  "donedate": "2020-04-03 14:29:22.975662",
  "nchannels": 1,
  "recvtz": [
    "EDT",
    -14400
  ],
  "streamtags": {
    "model": "eng-us:callcenter"
  },
  "ended": "2020-04-03 14:29:22.976576",
  "confidence": 0.88,
  "utterances": [
    {
      "confidence": 0.88,
      "end": 1.34,
      "recvtz": [
        "EDT",
        -14400
      ],
      "start": 0.05,
      "donedate": "2020-04-03 14:29:22.975662",
      "recvdate": "2020-04-03 14:28:59.488266",
      "events": [
        {
          "confidence": 0.98,
          "end": 0.41,
          "start": 0.05,
          "word": "Hello"
        },
        {
          "confidence": 0.84,
          "end": 1.34,
          "start": 0.5,
          "word": "earthlings."
        }
      ],
      "metadata": {
        "source": "Hello_Earthlings.wav",
        "model": "eng-us:callcenter",
        "uttid": 0,
        "channel": 0
      }
    }
  ],
  "source": "Hello_Earthlings.wav",
  "audiosecs": 1.43,
  "model": "eng-us:callcenter",
  "recvdate": "2020-04-03 14:28:59.488266"
}
In this section:

A transcript and associated metadata produced from an audio file, in JSON format. The Voci JSON format is documented in the Voci JSON Output Format Guide.