Documenti

Chunguza jinsi unavyoweza kutafsiri kwa bidii maombi yako kwa kutumia mfumo wetu sahili wa RES API.

Kuanza

Tafsiri ya TranslatePI inaandaa tamko sahili la kutafsiri maandishi kati ya lugha 180+. MILI hurudisha miitikio ya JSON.

Base URUL: https://api.translateapi.ai/api/v1/
Mwanzo wa Haraka

Fanya ombi lako la kwanza la tafsiri:

curl -X POST https://api.translateapi.ai/api/v1/translate/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "text": "Hello, world!",
    "target_language": "es"
  }'
import requests

response = requests.post(
    "https://api.translateapi.ai/api/v1/translate/",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "text": "Hello, world!",
        "target_language": "es"
    }
)

result = response.json()
print(result["translated_text"])  # "Hola, mundo!"
const response = await fetch("https://api.translateapi.ai/api/v1/translate/", {
    method: "POST",
    headers: {
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    body: JSON.stringify({
        text: "Hello, world!",
        target_language: "es"
    })
});

const result = await response.json();
console.log(result.translated_text);  // "Hola, mundo!"
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
using Newtonsoft.Json;

class Program
{
    static async Task Main()
    {
        var client = new HttpClient();
        client.DefaultRequestHeaders.Add(
            "Authorization", "Bearer YOUR_API_KEY"
        );

        var content = new StringContent(
            JsonConvert.SerializeObject(new {
                text = "Hello, world!",
                target_language = "es"
            }),
            Encoding.UTF8,
            "application/json"
        );

        var response = await client.PostAsync(
            "https://api.translateapi.ai/api/v1/translate/",
            content
        );

        var result = await response.Content.ReadAsStringAsync();
        var data = JsonConvert.DeserializeObject<dynamic>(result);
        Console.WriteLine(data.translated_text);  // "Hola, mundo!"
    }
}

Kupatana

Taja maombi yako kwa kutumia ufunguo wa API. Unaweza kutengeneza funguo za API bodi.

Ufasiri wa Kichwa (Kutangazwa)
Authorization: Bearer ta_your_api_key_here
Juzi ya Query Paramter
https://api.translateapi.ai/api/v1/translate/?api_key=ta_your_api_key_here
Dumisha funguo zako zikiwa salama! Usiwafunue katika mfumo wa siri wa wateja au kwenye maduka ya umma.

Tafsiri Sahihi

Kitafsiri ujumbe kwa lugha moja tu inayolengwa.

POST https://api.translateapi.ai/api/v1/translate/
Kuomba Msamaha
Penseli Aina Zahitajiwa Maelezo
text string Ndiyo Maandishi ya kutafsiri (sax herufi 50,000)
target_language string Ndiyo* Target language code (e.g., "es", "fr", "de")
source_language string Hapana Source language code. Default: "auto" (auto-detect)

* Matumizi target_language lugha moja au zaidi target_languages Kwa walio wengi, bila ya shaka watakuwa wengi, Tafsiri ya Lugha Mbalimbali.

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

Tafsiri ya Lugha Mbalimbali

Kitafsiri ujumbe kwa lugha mbalimbali kwa ombi moja tu.

Dokezo: Unaweza kutafsiri lugha 50 hivi katika ombi moja.
POST https://api.translateapi.ai/api/v1/translate/
Kuomba Msamaha
{
    "text": "Hello, world!",
    "target_languages": ["es", "fr", "de", "ja"],
    "source_language": "en"
}

Matumizi target_languages (arra) badala ya target_language Kwa ajili ya malengo mbalimbali.

Itikio
{
    "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
}

Tafsiri ya Banch

Tengeneza maandiko mengi mara moja kwa utayarishaji wa asnic. Ogea fungu la maneno na kura kwa ajili ya matokeo.

Mipaka: miandiko 500 kwa kila kirubali, x 750 kwa jumla (habari zinazolenga lugha). Kazi huchukua muda wa dakika 30 baada ya utayarishaji kuanza (wakati wa kungoja hauhesabiwi).
Wakati wa kusafiri hutofautiana kwa lugha: lugha za kawaida (Kihispania, Kifaransa, Kijerumani, n.k.) hutumia violezo vya kasi (0.1 kwa kila andiko), ilhali lugha ambazo si za kawaida sana hutumia mfano wetu mkubwa wa lugha za kilugha (0-5 kwa kila maandishi). Hati 100 ya kompyuta huwa na urefu wa sekunde 10-30 kwa ajili ya lugha za kawaida, au dakika 2-5 kwa ajili ya lugha za kawaida zisizo za kawaida. Kwa matokeo bora zaidi, tumia lugha 1 kwa maombi na huweka safu chini ya maandiko 50.
POST https://api.translateapi.ai/api/v1/translate/batch/
Hatua ya 1: Mjitiishe Chini ya Mtihani
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"
}'
Itikio (HTP 202 Yakubaliwa)
{
    "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/"
}
Hatua 2: Kuchavusha ili Kupata Matokeo
GET https://api.translateapi.ai/api/v1/jobs/{job_id}/
Kuchavusha Mfano (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"Completed: {processed}/{total} texts in {result.get('processing_time', 0):.1f}s")
        translations = result["result_data"]["translations"]
        break
    elif status == "failed":
        print(f"Failed at {processed}/{total}: {result.get('error_message', 'unknown')}")
        raise Exception(result.get("error_message", "Translation failed"))
    elif status == "pending":
        queue_pos = result.get("queue_position", "?")
        print(f"Queued (position {queue_pos}) — waiting for GPU worker...")
    else:
        print(f"[{status}] {processed}/{total} ({progress:.0f}%)")

    time.sleep(3)
Itikio (linayopangwa mistari, likisubiri GPU)
{
    "job_id": "67535b2b-...",
    "status": "pending",
    "processed_texts": 0,
    "total_texts": 3,
    "progress_percentage": 0.0,
    "queue_position": 3
}
Itikio (wakati wa utayarishaji)
{
    "job_id": "67535b2b-...",
    "status": "processing",
    "processed_texts": 1,
    "total_texts": 3,
    "progress_percentage": 33.33,
    "queue_position": null
}
Itikio (likamilishwa)
{
    "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
    }
}
Maendeleo ya Wakati Halisi

Kila jibu la kura ya maoni linajumuisha nyanja za maendeleo ya muda mrefu ili uweze kuangalia kile hasa kinachoendelea na shughuli zako:

Field Maelezo
status Kazi ya sasa inasema: pending Na anaye jitendea mwenyewe kheri basi bila ya shaka Mwenyezi Mungu ni Mwenye shukrani na Mjuzi. processing (tafsiri yenye utendaji), completed, failed
processed_texts Hesabu ya tafsiri moja - moja iliyokamilishwa hadi sasa.
total_texts Jumla ya tafsiri katika kigae hiki (habari zinazolenga lugha).
progress_percentage Asilimia kamili (0-100). ilikadiriwa kutokana na habari zilizotayarishwa_exts / refall_exts.
queue_position Nafasi yako katika foleni wakati ambapo hadhi "inapanda" (1 = halafu).
processing_time Wakati kamili wa utengenezaji kwa sekunde chache (upatikane unapokamilika).
Dokezo: Wakati status ni "pending", wafanyakazi wa GPU wana shughuli nyingi na mizigo mingine. queue_position Ili kuona ni kazi ngapi zitakazochukua nafasi yako (1 = unafuata). Kazi yako itaanza bila jitihada yoyote, endelea tu kupiga kura.
Mazoea Bora kwa Ajili ya Wafanyakazi Wengi
  • Andika lugha 1 kwa kila jambo unaloomba, na hilo hufanya kila kikundi kisafiri haraka na kufanya maendeleo kwa urahisi ili kiweze kufuatilia.
  • Weka makala kwenye kurasa 50-100. Malango madogo hukamilika haraka zaidi na kukupa makala mpya za mara kwa mara zaidi.
  • Kimbia katika zaidi ya nafasi mbili za kazi za pamoja. GPU huratibu mafungu 2 katika foleni za ziada za kazi zinazolingana na hizo na hautaanza haraka zaidi.
  • Baada ya muda, kazi hiyo inaweza kuendelea kufanywa tena kwenye mtandao wa GPU.
  • Kuchavusha kila sekunde 3 hadi5. kura zaidi ya mara kwa mara haiendeshi matayarisho.
Batch wa Ng'ambo

Hutafsiri maandiko mbalimbali katika lugha mbalimbali mara moja:

{
    "texts": ["Hello", "Goodbye"],
    "target_languages": ["es", "fr"],
    "source_language": "en"
}
Matokeo kamili_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
}
Vipindi vya Kuomba Msaada
Penseli Aina Zahitajiwa Maelezo
texts array Ndiyo File ya nyuzi za kutafsiri
target_language string Ndiyo* Mfumo wa lugha unaolengwa wa lugha kwa ajili ya lugha moja
target_languages array Ndiyo* Alama za lugha zinazolengwa za lugha mbalimbali
source_language string Hapana Source language code. Default: "auto"

* Andaa ama target_language au target_languages, si vyote viwili.

Uandaaji wa Async: Battch anaomba warudi mara moja kwa kutumia kifaa fulani job_id. Polar GET /api/v1/jobs/{job_id}/ mpaka status ni "completed", kisha soma result_data matumizi ya tafsiri mbalimbali progress_percentage ili kuchunguza maendeleo.

Document Translation

Pakua hati nzima - nzima huku ukihifadhi muundo. Hutegemeza miundo mbalimbali ya faili.

POST https://api.translateapi.ai/api/v1/translate/document/
Maombi (sehemu/form-data)
Penseli Aina Zahitajiwa Maelezo
file file Ndiyo Hati ya kutafsiri (max 10MB)
target_language string Ndiyo Target language code (e.g., "es", "fr", "de")
source_language string Hapana Source language code. Default: "auto" (auto-detect)
Aina za Faili Zinazotegemezwa
  • .txt - Thibitisha faili za maandishi
  • .docx - Hati za Neno
  • .pdf - Hati za PDF (kutia ndani habari iliyochunguzwa upya)
  • .json - faili za JSON (zitafsiri kanuni za uzi)
  • .xml - Mafaili ya XML
  • .srt - Mafaili yaliyohifadhiwa
  • .po / .pot - Tafuta faili za kutafsiri habari
  • .jpg / .jpeg - Picha za JPEG (OCR)
  • .png - PNG picha (OCR)
  • .tiff / .tif - TIFFE picha (OCR)
  • .bmp - Picha za BMP (OCR)
  • .webp - Picha za WebP (OCR)
Uungaji mkono WA OCR: Mafaili ya picha na picha ya PDF hutayarishwa kwa utambuzi wa herufi (OCR) ili kupata maandishi kabla ya kutafsiriwa. Kwa matokeo bora zaidi, tumia picha zilizo wazi, zilizo wazi.
Mfano (URL)
# 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"
Mafaili ya picha hutayarishwa na OCR ili kupata maandishi kabla ya kutafsiriwa. .txt faili.
Itikio
{
    "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"
}
Viwango
pending File akiwa amepakiwa, akisubiri kutenganishwa
processing Kazi ya kutafsiri inaendelea
completed Utafsiri ukiwa kamili, pakiaji unapatikana
failed Utafsiri haukufaulu (kuondoa makosa_mesage)
GET https://api.translateapi.ai/api/v1/translate/document/{id}/

Chunguza tarehe ya tafsiri ya hati au pokea nakala ya tafsiri ya URL.

Itikio
{
    "id": 123,
    "original_filename": "document.docx",
    "status": "completed",
    "translated_file_url": "/media/translated/document_es.docx",
    "character_count": 5420
}

Ugunduzi wa Lugha

Kugunduliwa kwa lugha kunafanywa katika kila ombi la kutafsiri. source_language to "auto" (au uuondoe) na lugha inayogunduliwa inarudishwa kwa itikio.

POST https://api.translateapi.ai/api/v1/translate/
Kuomba Msamaha
{
    "text": "Bonjour, comment allez-vous?",
    "target_language": "en"
}
Itikio
{
    "translated_text": "Hello, how are you?",
    "source_language": "fr",
    "target_language": "en",
    "translations": {
        "en": "Hello, how are you?"
    },
    "character_count": 28,
    "translation_time": 0.52
}

Ile source_language Eneo katika majibu yake linaonesha lugha iliyogunduliwa wakati mfumo wa mkojo unapotumiwa.

Lugha Zinazoungwa Mkono

Tafuta orodha ya lugha zote zinazotegemezwa.

GET https://api.translateapi.ai/api/v1/translate/languages/
Itikio
{
    "count": 186,
    "results": [
        {"iso": "en", "name": "English", "en_label": "English"},
        {"iso": "es", "name": "Español", "en_label": "Spanish"},
        {"iso": "fr", "name": "Français", "en_label": "French"},
        ...
    ]
}

Mifano ya Kutafsiri

Tunatumia vianzo vya kisasa vya kutafsiri vya serikali vinavyoendeshwa kwenye mfumo wetu wenyewe wa GPU.

Mfano Lugha Bora Zaidi
Helsinki-NLP/opus-mt 50+ Lugha tofauti - tofauti Lugha za kawaida (EN, ES, FR, DE, WE, PT, RU, ZH, JA, n.k.)
Google MADLAD-400 Lugha 400+ Lugha ambazo hazina maandishi mengi, na habari kamili

API huchagua kiolezo bora zaidi kwa ajili ya wenzi wa lugha yako kwa hiari. engine parameta:

Injini Maelezo
"auto" Default.Tries HugFace kwanza, hurudi MADLAD-00
"huggingface" Kikosi cha Kusambaza Habari/MarianMT (lugha imara zaidi, 50+)
"madlad" Force MADLAD-00 (lugha 2,400+)

Kushughulikia Vibaya

API hutumia kanuni za kiwango cha HTTP kuonyesha mafanikio au kushindwa.

Kanuni Maelezo
200 Mafanikio
400 Maombi Mabaya - Hali ya Chini ya Pamita
401 Ukosefu wa Haki - Hushindwa au Hukosekana Ufunguo wa API
402 Gharama ya Kila Siku Yapita Kiasi cha Mali
429 Maombi Mengi Mno - Viwango Vyapita Kiasi
503 Utumishi wa injini isiyoweza kutafsiriwa kwa urahisi
Itikio Lisilofaa Latokezwa
{
    "error": "daily_limit_exceeded",
    "credits_remaining": 0,
    "daily_limit": 100000
}

Mipaka ya Kiwango

Weka mipaka kwa njia tofauti - tofauti kwa kupanga mambo. " unyoo " kwa maelezo kamili:

Panga Characters/Month Bei
Huru 250,000 $0 Fanyeni Ishara kwa Hiari
keyboard label 2,500,000 $9/mo print operation status
Project 10,000,000 $29/mo print operation status
Biashara 40,000,000 $79/mo print operation status
Magamba 125,000,000 $199/mo print operation status

Ukivuka mpaka wako, utapokea 429 Too Many Requests Jibu ni mpaka mwezi ujao au uwe mwepesi zaidi.

Auto-Scaling Cloud Infrastructure

TranslateAPI runs on dedicated NVIDIA A100 GPU instances with automatic horizontal scaling. When demand increases, additional GPU instances are launched within minutes to maintain fast response times. This means our API can handle virtually unlimited concurrent requests without degradation — from a single request to thousands per minute.

Pima ukurasa huu
Asanteni kwa viwango vyenu!
/5 msingi viwango