Send a transcription request

post

https://vcloud.vocitec.com/transcribe

Customize transcription output as needed with request parameters. To receive transcription results, include a callback URL with your request or access them using the /transcribe/result endpoint.

Body Params

file

required

Specify a single .wav audio file or a ZIP archive containing multiple .wav audio files to transcribe. Refer to the transcode parameter to use audio formats other than .wav.

token

string

required

Unique string used to authenticate and authorize the request. All requests made with a token are linked to the associated account. Contact Voci support if you haven't received a token or if a token is lost or comprimised.

url

string

Use as an alternative to the file parameter for sending audio in a request. The provided URL must support HTTP GET and return a Content-Length header when queried. url supports HTTP basic authentication by prepending access credentials to the hostname of the URL as shown in the example. In addition, url also supports HTTP authorization request headers by including the authorization header, authorization type, and access credentials in the request.

callback

string

Provide a callback address for V-Cloud to send the results when the transcription process is complete. callback supports HTTP basic authentication by prepending access credentials to the hostname of the URL as shown in the example.

diarize

boolean

Defaults to false

Enable to identify distinct speakers on mono (single channel) audio and segment detected speech into separate channels, which are identified in JSON output.

emotion

boolean

Defaults to false

Enables the emotion detection feature that uses a synthesis of acoustic features and word sentiment scores to determine if a given utterance is Mostly Positive, Positive, Neutral, Negative, or Mostly Negative.

gender

boolean

Defaults to false

Enables the gender detection feature that attempts to determine if the speaker is "male" (stereotypically lower frequencies) or "female" (stereotypically higher frequencies) in each utterance.

metadata

string

Enables the inclusion of user-defined metadata in a top-level object of JSON transcripts.

model

string

Defaults to eng-us:callcenter

Specify the language model to use for transcription.

music

boolean

Defaults to false

Enables the music detection feature to pass all utterances through an algorithm to be classified as music or speech. Utterances classified as music are assumed to contain noisy audio and are not transcribed.

numtrans

boolean

Defaults to true

Enables the number translation feature to control whether or not number words in transcribed text are converted into numeric digits and related conventional formats, including dollar amounts, wall-clock times, percentages, ordinals, and telephone numbers.

output

string

enum

Defaults to json

Specify the desired output format for transcripts. Refer to output for more information on output formats.

Allowed:

outzip

boolean

Defaults to false

Enable to contain the results in a ZIP file.

punctuate

boolean

Defaults to true

Enables the punctuation feature to control whether transcript text is punctuated or not. In most cases, it is desirable to leave punctuation turned on.

scrubaudio

boolean

Defaults to false

Enables the redaction feature to redact audio. Redaction recognizes and removes sensitive numeric values from results. When this option is enabled, a ZIP file containing the redacted audio returns with the transcript.

scrubtext

boolean

Defaults to false

Enables the redaction feature to redact transcript text. Redaction recognizes and removes sensitive numeric values from results.

scrubconf

string

Define custom redaction rules using regular expression matches contained in a JSON object. Default redaction rules are already available when setting scrubtext to true. Refer to Redaction Rule Syntax for the correct syntax and Default Redaction File for best practices when developing redaction rules.

subst

boolean

Defaults to false

Enables automatic system and model-level substitutions.

substinfo

boolean

Defaults to false

Enable to provide substitution details in JSON transcripts.

subst_rules

string

Specify a newline-delimited string that contains substitution rules to apply during transcription.

transcode

boolean

Defaults to false

Enable to convert incoming audio into a supported format. transcode supports an extensive set of open audio formats. As our support for different formats changes frequently, submit your audio in a request to determine if the audio format is supported.

Headers

string

enum

Defaults to application/json

Generated from available response content types

Allowed:

Responses

200The transcription request was successful and returned a requestid to retrieve the results.

400The attempted request contains an invalid argument. Review the request for errors and try again.

401The request used an invalid token.

405The request used an invalid method.

500Indicates an internal issue with the V-Cloud server. Retry the request. If the issue persists, contact Voci support or check Voci Status.

502A required service for the request was inaccessible. If the request includes a URL audio source, there may be an issue with the connection to the remote file provider.

504The request was unable to complete within a reasonable amount of time. Retry the request. If the issue persists, contact Voci support or check Voci Status.