Phoneme & Classification

Synchronous classifier for an isolated French liquid/nasal recording (5 classes: l, m, n, ɲ, ʁ), built for the Aphasi…

post/api/classify-french-liquid-nasal

Request

  • Base URL: https://platform.vocametrix.com
  • URL: https://platform.vocametrix.com/api/classify-french-liquid-nasal
  • Auth: API key in header X-API-Key

Request body

audiostring required

Mode 1 (use ONE of audio/blobUrl/fileId). Direct audio file upload, multipart/form-data — the field name MUST be exactly audio.

blobUrlstring required

Mode 2 (use ONE of audio/blobUrl/fileId), JSON body. HTTPS URL of the audio file, downloaded server-side.

fileIdstring required

Mode 3 (use ONE of audio/blobUrl/fileId), JSON body. fileId from a prior /api/assignFileId upload.

expected_liquid_nasalstring

Optional (also accepted as expectedLiquidNasal, any input mode). When provided, the response is scored against this class.

Response

Successful response

successboolean

Boolean — true if the classification succeeded.

predicted_liquid_nasalstring

Predicted liquid/nasal (IPA).

confidencestring

Confidence for the predicted class (0.0 - 1.0).

all_probabilitiesobject

Object of probabilities for all 5 classes.

audio_durationnumber

Audio duration in seconds.

processing_time_secondsnumber

Server-side processing time in seconds.

model_namestring

Model used, e.g. "liquid-nasal-aphasix-champion".

expected_liquid_nasal (conditional)string

Echoed back only when expected_liquid_nasal/expectedLiquidNasal was provided in the request.

is_correct (conditional)boolean

Boolean — true when predicted_liquid_nasal matches expected_liquid_nasal.

expected_liquid_nasal_probability (conditional)string

The model's probability for expected_liquid_nasal, from all_probabilities.

score (conditional)integer

expected_liquid_nasal_probability rounded to a 0-100 integer.

Changes

No recorded changes to this operation across all 1 revision of this API.