API Documentation

Integrate yakasimba kushandurwa mumaapplication ako nedu nyore REST API.

Kutanga

The TranslateAPI inopa nyore REST interface for translating text between 180+ languages. All API endpoints return JSON responses.

Base URL: https://api.translateapi.ai/api/v1/
Kutanga Kwenguva pfupi

Kuita yako yekutanga chikumbiro chekushandurwa:

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!"
    }
}

Authentication

Authenticate yako zvikumbiro kushandisa API key. Unogona kuita API keys kubva yako dashboard.

Header Authentication (Recommended)
Authorization: Bearer ta_your_api_key_here
Query Parameter
https://api.translateapi.ai/api/v1/translate/?api_key=ta_your_api_key_here
Kuchengeta yako API mabhureki akachengeteka! Don’t expose them in client-side code or public repositories.

Kushandura Mitauro

Translate text to a single target language.

POST https://api.translateapi.ai/api/v1/translate/
Kukumbira muviri
Parameter _Ruvara: Inodiwa Kutaura
text string _Hapana Text to translate (max 50,000 characters)
target_language string Yeah* Target language code (e.g., "es", "fr", "de")
source_language string Hapana Source language code. Default: "auto" (auto-detect)

* Usati target_language (string) yeimwe rurimi kana target_languages (array) yezviuru. Ona Multi-Target Kushandura.

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

Multi-Target Kushandura

Translate text to multiple languages in a single request. Uses the same endpoint as single translation.

Nhanho: Iwe unogona kushandura kusvika 50 mitauro mune imwe mibvunzo.
POST https://api.translateapi.ai/api/v1/translate/
Kukumbira muviri
{
    "text": "Hello, world!",
    "target_languages": ["es", "fr", "de", "ja"],
    "source_language": "en"
}

_Use target_languages (array) sezviri target_language (string) kune akawanda zvinangwa.

Kubvunzana
{
    "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
}

Batch Kushandura

Translate multiple texts at once with async processing. Submit a batch and poll for results.

Restrictions: max 500 texts per batch, max 750 total items (texts × target languages).Jobs time out 30 minutes after processing starts (queue waiting time is not counted).
Kugadziriswa kwenguva kunosiyana zvichienderana nezita remutauro: mitauro yakajairika (Spanish, French, German, etc.) inoshandisa mamodheru akasimba (~0.1s per text), asi mitauro inenge isiri yakajairika inoshandisa mamodheru edu makuru ane mitauro mizhinji (~1-3s per text). A 100-text batch inowanzo gadzirirwa mu10-30 seconds for common languages, or 2-5 minutes for less common ones. For best results, send 1 target language per batch request and keep batch sizes below 50 texts.
POST https://api.translateapi.ai/api/v1/translate/batch/
Step 1: Submit Batch
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"
}'
Response (HTTP 202 Accepted)
{
    "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/"
}
Step 2: Poll for Results
GET https://api.translateapi.ai/api/v1/jobs/{job_id}/
Polling Mufananidzo (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)
Response (inotarisirwa — kumirira, kumirira GPU)
{
    "job_id": "67535b2b-...",
    "status": "pending",
    "processed_texts": 0,
    "total_texts": 3,
    "progress_percentage": 0.0,
    "queue_position": 3
}
Response (panguva yekushanda)
{
    "job_id": "67535b2b-...",
    "status": "processing",
    "processed_texts": 1,
    "total_texts": 3,
    "progress_percentage": 33.33,
    "queue_position": null
}
Response (completed)
{
    "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
    }
}
Real-Time Progress Tracking

Every poll response inosanganisira real-time progress fields kuitira kuti iwe ugone kuongorora zvakajeka zvazvinoitika nebasa rako:

Nzvimbo Kutaura
status Current job state: pending (inomirira, iri kumirira GPU nyanzvi), processing (actively translating), completed, failed
processed_texts Nhamba yezvinyorwa zvakashandurwa kusvika parizvino. Zvinyorwa zvakashandurwa zvinovandudzwa munguva chaiyo sezvakashandurwa.
total_texts Total number of translations in this batch (texts × target languages).
progress_percentage Percentage of completion (0-100). Calculated from processed_texts / total_texts.
queue_position Nzvimbo yako musoro kana mamiriro ezvinhu ari "kutarisirwa" (1 = next up). Null kana achigadziriswa kana achipera. Dzvanya pano kuti ugone kufungidzira nguva yekumirira uye kuti uone mamiriro ezvinhu esoro kune vashandisi vako.
processing_time Total processing time in seconds (available when completed).
Nhanho: Kana status is "pending", the GPU workers are busy with other batches. Check queue_position kuti uone kuti mabasa mangani ari pamberi peako (1 = iwe uri kutevera). Basa rako richatanga otomatiki — hapana chinhu chinodiwa, chete chengetedza polling.
Best Practices for Large Workloads
  • Send 1 target language per batch request. This keeps each batch fast and makes progress easy to track.
  • Keep batches at 50-100 texts. Smaller batches kuenderera mberi nekukurumidza uye kukupa iwe zvakawanda zvakajairika kuenderera mberi updates.
  • GPU inogadzirisa 2 batchs zvakaenzana — zvimwe mabasa anomirira uye haazotanga nekukurumidza.
  • Panguva pfupi, re-poll iyo job_id kunze kwekutumira nyowani batch. Iyo yekutanga basa inogona kunge iri kugadziriswa paGPU.
  • Poll every 3-5 seconds. More frequent polling does not speed up processing.
Multi-language batch

Translate multiple texts to multiple languages at once:

{
    "texts": ["Hello", "Goodbye"],
    "target_languages": ["es", "fr"],
    "source_language": "en"
}
Result_data yakapera
{
    "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 yechikumbiro
Parameter _Ruvara: Inodiwa Kutaura
texts array _Hapana Array of strings to translate
target_language string Yeah* Target language code for single language
target_languages array Yeah* Array of target language codes for multiple languages
source_language string Hapana Source language code. Default: "auto"

* Kupa kana target_language kana target_languages, kwete zvese.

Async Kugadziriswa: Batch zvikumbiro kudzoka nguva dzose ne job_id. Poll GET /api/v1/jobs/{job_id}/ kusvika status is "completed", wobva waverenga result_data for translations. Use progress_percentage to track progress.

Kushandurwa kweDokumenti

Kushandura yose mapepa achichengeta kuumbwa. Supports multiple file formats.

POST https://api.translateapi.ai/api/v1/translate/document/
Chikumbiro (multipart/form-data)
Parameter _Ruvara: Inodiwa Kutaura
file file _Hapana Chinyorwa chekushandura (max 10MB)
target_language string _Hapana Target language code (e.g., "es", "fr", "de")
source_language string Hapana Source language code. Default: "auto" (auto-detect)
Anotsigirwa File Types
  • .txt - Plain text files
  • .docx - Mabhuku eWord
  • .pdf - PDF mafaera (kusanganisira scanned)
  • .json - JSON mafaera (anoshandura mavara e string)
  • .xml - XML mafaera
  • .srt - Subtitle mafaera
  • .po / .pot - Gettext kushandura mafaera
  • .jpg / .jpeg - JPEG mifananidzo (OCR)
  • .png - PNG mifananidzo (OCR)
  • .tiff / .tif - TIFF mapikicha (OCR)
  • .bmp - BMP mifananidzo (OCR)
  • .webp - WebP mifananidzo (OCR)
OCR rutsigiro: Image mafaera uye scanned PDFs zvinogadziriswa ne Optical Character Recognition (OCR) kuti uwane tenzi usati washandura. Kuti uwane mhedzisiro yakanaka, shandisa mapikicha akajeka ane resolution yepamusoro.
Mufananidzo (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"
Image files are processed with OCR to extract text before translation. The translated output is returned as .txt faira.
Kubvunzana
{
    "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"
}
Status Values
pending File uploaded, waiting to be processed
processing Kushandurwa kuri kuitwa
completed Kushandurwa kwakamisikidzwa, kurodha pasi kuripo
failed Translation failed (check error_message)
GET https://api.translateapi.ai/api/v1/translate/document/{id}/

Check the status of a document translation or retrieve the download URL.

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

Kuwana Zvinhu

Chirungu detection inowanikwa mune yega yega yekushandura mibvunzo. Set source_language to "auto" (kana kuisa pasi) uye mutauro wakawanikwa unodzokera mubvunzo.

POST https://api.translateapi.ai/api/v1/translate/
Kukumbira muviri
{
    "text": "Bonjour, comment allez-vous?",
    "target_language": "en"
}
Kubvunzana
{
    "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
}

The source_language field in the response shows the detected language when auto-detection is used.

Zvinhu zvinotsigirwa

Get the list of all supported languages.

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

Kushandura Models

Isu tinoshandisa state-of-the-art open source kushandura mamodheru ari kushanda pane yedu GPU infrastructure. All models are commercially licensed (Apache 2.0).

Model Zvinhu Best For
Helsinki-NLP/opus-mt 50+ mitauro miviri Zvimwe zvinyorwa (EN, ES, FR, DE, IT, PT, RU, ZH, JA, etc.)
Google MADLAD-400 400 + mitauro Zvinhu zvisina kumbobvira zvataurwa, kuongororwa kwakadzama

The API otomatiki anosarudza yakanakisisa model for your language pair. You can optionally specify an engine parameter:

Injini Kutaura
"auto" Zviripachena. Inoedza HuggingFace yekutanga, inodzokera ku MADLAD-400
"huggingface" Force HuggingFace/MarianMT (inokurumidza, 50+ mitauro)
"madlad" Force MADLAD-400 (400+ mitauro)

Kugadziriswa kwematambudziko

Iyo API inoshandisa standard HTTP status codes kuti iratidze kubudirira kana kukundikana.

Code Kutaura
200 Kubudirira
400 Bad Request - Invalid parameters
401 Unauthorized - API key isina mvumo kana isina kuwanikwa
402 Kubhadharwa Kunodiwa - Daily character quota exceeded
429 Zvikumbiro zvakawandisa - huwandu hwemiganhu hwakakwira
503 Service Unavailable - Translation engine temporarily down
Mufananidzo wemufananidzo
{
    "error": "daily_limit_exceeded",
    "credits_remaining": 0,
    "daily_limit": 100000
}

Zvirambidzo zvemutengo

Zvirambidzo zvinosiyana zvichienderana nechirongwa. Ona pricing for full details:

Plan Characters/Month Mutengo
Vakasununguka 250,000 $0 Sign Up Free
Starter 2,500,000 $9/mwedzi Kugamuchirwa
Pro 10,000,000 $29/mwedzi Kugamuchirwa
Bhizinesi 40,000,000 $79/mwedzi Kugamuchirwa
S_cale 125,000,000 $199/mwedzi Kugamuchirwa

Kana iwe ukakwira chiyero chako, iwe uchawana 429 Too Many Requests mashoko kusvika kumwedzi unouya kana iwe kuvandudzwa.

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.

Ratidza iyi peji
Thank you for your rating!
/5 Zvinoenderana ne ratings