POST
/
api
/
ai
/
speech-text
curl --request POST \
  --url https://api.worqhat.com/api/ai/speech-text \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form keep_fillers=false \
  --form enable_formatting=true \
  --form enable_profanity_filters=true
{
  "data": {
    "text": "<string>",
    "speaker_labels": [
      {
        "speaker": "<string>",
        "text": "<string>"
      }
    ],
    "timestamps": [
      {
        "word": "<string>",
        "start_time": 123,
        "end_time": 123,
        "duration": 123
      }
    ],
    "processingTime": 123,
    "processingId": "<string>",
    "processingCount": 123
  }
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-data
Upload an audio file for speech-to-text processing.
​
audio
file
required

The audio file to be transcribed.

​
keep_fillers
boolean
default:false

Keep filler words like "um" and "uh".

​
enable_formatting
boolean
default:true

Enable text formatting (punctuation, capitalization, etc.).

​
enable_profanity_filters
boolean
default:true

Enable filters to censor profane words.

Response

200
application/json
Speech successfully converted to text
​
data
object
required

Was this page helpful?