Voice Enrollment

Service that generates a voice template from the captured audios and returns the validation result of each audio.

Endpoint

POST /biometric/voice/enrollment

Headers

Name	Type	Required	Description
Authorization	string	Yes	Consumer Token in Bearer format Bearer <token>. See Authentication.
consumer-id	string	Yes	Consumer identifier.

Request body

Content-Type: application/json

Parameters

Parameter	Type	Required	Description
audios	array	Yes	Capture audios, in Base64, in recording order.

Request example

{
  "audios": ["<base64 audio 1>", "<base64 audio 2>", "<base64 audio 3>"]
}

Responses

200 Success

Response parameters

Parameter	Type	Description
consumerId	string	Identifier of the consumer that made the call.
transactionId	string	Transaction identifier.
timestamp	string	Response timestamp in format ISO 8601.
message	string	Descriptive field for the result of the service execution.
operationResult	integer	Result code of the service execution.
template	string	Resulting voice template.
templateType	string	Type of generated template.
validateAudiosResult	array	Per audio result. See Per audio result.

Per audio result

Parameter	Type	Description
audio_position	integer	Audio position in the request.
result_code	integer	Audio result code.
matching_score	number	Audio matching score.
snr_db_detected	number	Detected signal-to-noise ratio, in decibels.
speech_length_ms_detected	integer	Detected speech duration, in milliseconds.
speech_relative_length_detected	number	Speech proportion relative to total duration.
multiple_speakers_score_detected	number	Multiple speakers detection score.

Other responses

Code	Description
400	Required field missing or unsupported audio format.
401	Missing, invalid, or expired Token.
403	The consumer is not provisioned with the service VOICE_ENROLLMENT.

The body of an error response has the form described in MIDAPI v2.