Dokumentatioun

Ufrokörper

* Gebrauch target_language (String) fir eng eenzeg Sprooch oder target_languages (Array) fir multiple. See Multi-Target Iwwersetzung.

Äntwert

{
    "translated_text": "Hola, mundo!",
    "source_language": "en",
    "target_language": "es",
    "translations": {
        "es": "Hola, mundo!"
    },
    "character_count": 13,
    "translation_time": 0.45
}

Ufrokörper

{
    "text": "Hello, world!",
    "target_languages": ["es", "fr", "de", "ja"],
    "source_language": "en"
}

Verwenden target_languages (Array) anstatt target_language (String) fir méi Zieler.

Äntwert

{
    "source_language": "en",
    "translations": {
        "es": "Hola, mundo!",
        "fr": "Bonjour, monde!",
        "de": "Hallo, Welt!",
        "ja": "こんにちは、世界！"
    },
    "character_count": 52,
    "translation_time": 2.31
}

Schrëtt 1: Batch schécken

curl -X POST https://api.translateapi.ai/api/v1/translate/batch/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "texts": ["Hello", "Goodbye", "Thank you"],
    "target_language": "es",
    "source_language": "en"
}'

Antwort (HTTP 202 akzeptéiert)

{
    "job_id": "67535b2b-c9e3-4f82-9499-e237edbc1dd8",
    "status": "pending",
    "total_texts": 3,
    "queue_position": 1,
    "source_language": "en",
    "target_languages": ["es"],
    "character_count": 22,
    "credits_remaining": -1,
    "poll_url": "https://api.translateapi.ai/api/v1/jobs/67535b2b-c9e3-4f82-9499-e237edbc1dd8/"
}

Schrëtt 2: Umfro fir Resultater

Lëscht vu lëtzebuergeschen Dichter (Python)

import time, requests

job_id = response.json()["job_id"]
total = response.json()["total_texts"]
headers = {"Authorization": "Bearer YOUR_API_KEY"}

print(f"Batch submitted: {total} texts (job {job_id})")

while True:
    result = requests.get(f"https://api.translateapi.ai/api/v1/jobs/{job_id}/", headers=headers).json()
    status = result["status"]
    processed = result.get("processed_texts", 0)
    progress = result.get("progress_percentage", 0)

    if status == "completed":
        print(f"Done: {processed}/{total} in {result.get('processing_time', 0):.1f}s")
        translations = result["result_data"]["translations"]
        break
    elif status == "failed":
        raise Exception(result.get("error_message", "Translation failed"))
    elif status == "pending":
        print(f"Queued (position {result.get('queue_position', '?')})")
    else:
        print(f"[{status}] {processed}/{total} ({progress:.0f}%)")

    time.sleep(3)

Antwort (vollstänneg)

{
    "job_id": "67535b2b-...",
    "status": "completed",
    "processed_texts": 3,
    "total_texts": 3,
    "progress_percentage": 100.0,
    "processing_time": 10.65,
    "result_data": {
        "translations": ["Hola", "Adiós", "Gracias"],
        "source_language": "en",
        "target_language": "es",
        "character_count": 22,
        "processing_time": 10.65
    }
}

Echtzäit-Fortschrittsverfolgung

Multi-Language Batch

Méi Texter a méi Sproochen op eemol iwwersetzen:

{
    "texts": ["Hello", "Goodbye"],
    "target_languages": ["es", "fr"],
    "source_language": "en"
}

Completed result_data

{
    "translations": [
        {"es": "Hola", "fr": "Bonjour"},
        {"es": "Adiós", "fr": "Au revoir"}
    ],
    "source_language": "en",
    "target_languages": ["es", "fr"],
    "character_count": 24,
    "processing_time": 2.45
}

Parameter ufroen

* Gitt entweder target_language oder target_languages, net béid.

Best Practices for Large Workloads

• 1 Zilsprooch pro Batch- Ufro schécken. Dat hält all Batch séier a mécht de Fortschritt einfach ze verfolgen.
• Halt Batchs bei 50- 100 Texter. Kleng Batchs sinn méi séier fäerdeg a ginn Iech méi dacks Fortschrittsaktualiséierungen.
• Setzt sou vill Batch-Aufgaben un, wéi Dir braucht - eise GPU-Cluster skaléiert automatesch fir d'Bedierfnes ze bewältegen. D'Aufgaben ginn parallel iwwer méi Instanzen veraarbecht.
• No Timeout, déi selwecht job_id erëm froen, anstatt en neie Batch ze schécken. Den urspréngleche Job kann nach ëmmer op der GPU veraarbecht ginn.
• Frot all 3- 5 Sekonnen. Méi heefeg Froen beschleunegen d' Veraarbechtung net.

Ufro (multipart/form-data)

Ënnerstëtzt Dateitypen

Beispill (cURL)

# Translate a Word document
curl -X POST https://api.translateapi.ai/api/v1/translate/document/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@document.docx" \
  -F "target_language=es" \
  -F "source_language=en"

# Translate text from an image (OCR)
curl -X POST https://api.translateapi.ai/api/v1/translate/document/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@scanned_page.jpg" \
  -F "target_language=es" \
  -F "source_language=en"

Äntwert

{
    "id": 123,
    "original_filename": "document.docx",
    "file_type": "docx",
    "source_language": "en",
    "target_language": "es",
    "status": "completed",
    "character_count": 5420,
    "translated_file_url": "/media/translated/document_es.docx",
    "created_at": "2024-01-15T10:30:00Z",
    "completed_at": "2024-01-15T10:30:05Z"
}

Den Status vun der Iwwersetzung vun engem Dokument iwwerpréiwen oder d'URL vum Download kréien.

Statuswäerter

Äntwert

{
    "count": 186,
    "results": [
        {"iso": "en", "name": "English", "en_label": "English"},
        {"iso": "es", "name": "Español", "en_label": "Spanish"},
        {"iso": "fr", "name": "Français", "en_label": "French"},
        ...
    ]
}

186 Säiten.