Examples

1) GET /status (public)

cURL

curl

curl -X GET "https://api-endpoints.alphaedge-ai.com/status"

Python

python

import requests
r = requests.get("https://api-endpoints.alphaedge-ai.com/status", timeout=30)
print(r.status_code, r.json())

TypeScript

typescript

const res = await fetch("https://api-endpoints.alphaedge-ai.com/status");
console.log(res.status, await res.json());

HTTP 200 response:

json

{
  "status": "ok",
  "response_ms": 0.02,
  "version": "0.3.0",
  "uptime_seconds": 367.89,
  "checks": { "asr": true, "ocr": true }
}

2) GET /models (public catalog, no API key)

cURL

curl

curl -X GET "https://api-endpoints.alphaedge-ai.com/models"

Python

python

import requests
r = requests.get("https://api-endpoints.alphaedge-ai.com/models", timeout=30)
print(r.status_code, r.json())

TypeScript

typescript

const res = await fetch("https://api-endpoints.alphaedge-ai.com/models");
console.log(res.status, await res.json());

HTTP 200 response — array of objects (no envelope):

json

[
  { "model_slug": "alpha-audio-v1", "type": "audio" },
  { "model_slug": "alpha-digit-max", "type": "ocr" },
  { "model_slug": "alpha-digit-medium", "type": "ocr" }
]

3) GET /models/{model_slug} (model details, public)

Returns the metadata of a model: exposed endpoints, name of the input multipart field, accepted boolean options, accepted file extensions and pricing.

curl

curl -X GET "https://api-endpoints.alphaedge-ai.com/models/alpha-audio-v1"

HTTP 200 response (audio example):

json

{
  "model_slug": "alpha-audio-v1",
  "type": "audio",
  "display_name": "AlphaAudio v1",
  "version": "1.0",
  "description": "ASR haute précision optimisé pour le français.",
  "endpoints": [
    "POST /models/alpha-audio-v1/transcript"
  ],
  "input_field_name": "audio",
  "optional_fields": ["enable_diarization", "enable_postcorrect"],
  "accepted_extensions": ["mp3", "m4a", "wav", "flac", "ogg", "opus", "webm", "wma", "aiff", "aac", "aif"],
  "pricing": {
    "eur_per_hour": 0.15,
    "billing_unit": "audio_duration_seconds",
    "currency": "EUR"
  }
}

If the slug does not exist: 404 {"detail": "Modèle introuvable."}

4) POST /models/{model_slug}/transcript (audio -> text)

multipart/form-data parameters:

audio (required)
enable_diarization (optional)
enable_postcorrect (optional — linguistic post-correction via an external open-source model hosted at Novita, French only)

Synchronous HTTP 200 response with the transcribed text in the field text.

Accepted boolean values (case-insensitive): 1/0, true/false, yes/no, on/off. Any other value returns an explicit 422.

cURL

curl

curl -X POST "https://api-endpoints.alphaedge-ai.com/models/alpha-audio-v1/transcript" \
  -H "X-API-Key: TA_CLE" \
  -F "audio=@/chemin/audio.wav" \
  -F "enable_diarization=true"

Python

python

import requests
url = "https://api-endpoints.alphaedge-ai.com/models/alpha-audio-v1/transcript"
headers = {"X-API-Key": "TA_CLE"}
with open("/chemin/audio.wav", "rb") as f:
    files = {"audio": ("audio.wav", f, "audio/wav")}
    data = {
        "enable_diarization": "true",
    }
    r = requests.post(url, headers=headers, files=files, data=data, timeout=300)
print(r.status_code)
print(r.json())

TypeScript (Node.js)

typescript

import fs from "node:fs";
const form = new FormData();
form.append("audio", new Blob([fs.readFileSync("/chemin/audio.wav")]), "audio.wav");
form.append("enable_diarization", "true");
const res = await fetch("https://api-endpoints.alphaedge-ai.com/models/alpha-audio-v1/transcript", {
  method: "POST",
  headers: { "X-API-Key": "TA_CLE" },
  body: form
});
console.log(res.status, await res.json());

5) POST /models/{model_slug}/ocr (image -> text)

Paramètres multipart/form-data :

image (obligatoire, fichier)
pdf_password (optionnel)
enable_bbox (optionnel) — bounding boxes, +0,25 € / 1 000 pages
enable_extraction (optionnel) — extraction structurée, +0,50 € / 1 000 pages seulement si des données sont trouvées
extraction_prompt (optionnel, requis si enable_extraction) — champs séparés par des virgules

Doc complète : POST /models/{model_slug}/ocr

cURL

curl

curl -X POST "https://api-endpoints.alphaedge-ai.com/models/alpha-digit-max/ocr" \
  -H "X-API-Key: TA_CLE" \
  -F "image=@/chemin/facture.png" \
  -F "enable_bbox=true" \
  -F "enable_extraction=true" \
  -F "extraction_prompt=immatriculation, propriétaire, montant TTC"

Python

python

import requests
url = "https://api-endpoints.alphaedge-ai.com/models/alpha-digit-max/ocr"
headers = {"X-API-Key": "TA_CLE"}
with open("/chemin/facture.png", "rb") as f:
    files = {"image": ("facture.png", f, "image/png")}
    data = {
        "enable_bbox": "true",
        "enable_extraction": "true",
        "extraction_prompt": "immatriculation, propriétaire, montant TTC",
    }
    r = requests.post(url, headers=headers, files=files, data=data, timeout=300)
print(r.status_code)
print(r.json())

TypeScript (Node.js)

typescript

import fs from "node:fs";
const form = new FormData();
form.append("image", new Blob([fs.readFileSync("/chemin/facture.png")]), "facture.png");
form.append("enable_bbox", "true");
form.append("enable_extraction", "true");
form.append("extraction_prompt", "immatriculation, propriétaire, montant TTC");
const res = await fetch("https://api-endpoints.alphaedge-ai.com/models/alpha-digit-max/ocr", {
  method: "POST",
  headers: { "X-API-Key": "TA_CLE" },
  body: form
});
console.log(res.status, await res.json());