---
title: "Synchronous classifier for an isolated French vowel recording (11 classes: a, e, i, o, u, y, ø, ɑ̃, ɔ̃, ɛ, ɛ̃), built…"
method: POST
path: "/api/classify-french-vowel"
tags: ["Phoneme & Classification"]
---

# Synchronous classifier for an isolated French vowel recording (11 classes: a, e, i, o, u, y, ø, ɑ̃, ɔ̃, ɛ, ɛ̃), built…

`POST /api/classify-french-vowel`

## Request

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

## Request body

- object
  - `audio` string, required: Mode 1 (use ONE of audio/blobUrl/fileId). Direct audio file upload, multipart/form-data — the field name MUST be exactly `audio`. Accepts wav, webm, ogg, mp3 (converted server-side to WAV 16kHz mono).
  - `blobUrl` string, required: Mode 2 (use ONE of audio/blobUrl/fileId), JSON body. HTTPS URL of the audio file, downloaded server-side.
  - `fileId` string, required: Mode 3 (use ONE of audio/blobUrl/fileId), JSON body. fileId from a prior /api/assignFileId upload.
  - `expected_vowel` string: Optional (also accepted as expectedVowel, any input mode). When provided, the response is scored against this vowel.

## Response `200`

Successful response

- object
  - `success` boolean: Boolean — true if the classification succeeded.
  - `predicted_vowel` string: Predicted vowel (IPA).
  - `confidence` string: Confidence for the predicted vowel (0.0 - 1.0).
  - `all_probabilities` object: Object of probabilities for all 11 vowels, e.g. `{ "a": 0.009, "e": 0.91, ... }`.
  - `audio_duration` number: Audio duration in seconds.
  - `processing_time_seconds` number: Server-side processing time in seconds.
  - `model_name` string: Model used, e.g. "vowel-aphasix-champion".
  - `expected_vowel (conditional)` string: Echoed back only when expected_vowel/expectedVowel was provided in the request.
  - `is_correct (conditional)` boolean: Boolean — true when predicted_vowel matches expected_vowel.
  - `expected_vowel_probability (conditional)` string: The model's probability for expected_vowel, from all_probabilities.
  - `score (conditional)` integer: expected_vowel_probability rounded to a 0-100 integer. 90-100 excellent, 50-89 acceptable, 10-49 hard to recognize, 0-9 not recognized at all.

## Other responses

- `400`: Bad request — missing or invalid parameter
- `401`: Unauthorized — missing or invalid API key
- `429`: Rate limit exceeded
- `500`: Server error

---

[API](https://skmtc.dev/vocametrix/apis/vocametrix-api.md) · [All operations](https://skmtc.dev/vocametrix/apis/vocametrix-api/llms.txt) · [OpenAPI document](https://skmtc.dev/vocametrix/apis/vocametrix-api/revisions/8a54d01bcc81?raw)