Documentación da API

Integre unha poderosa tradución nas súas aplicacións coa nosa simple API REST.

Get Free API Key Endpoints Pricing

Comezar

A API de tradución fornece unha interface REST sinxela para traducir texto entre máis de 180 idiomas. Todos os puntos finais da API devolven respostas JSON.

1. Get Your API Key

Create a free account and generate your API key from the dashboard:

  1. Sign up at translateapi.ai/signup
  2. Go to Dashboard → Chaves da API
  3. Click "Create API Key" and copy your key

API keys start with ta_ followed by 56 hex characters.

URL base: https://api.translateapi.ai/api/v1/
2. Make Your First Request

Replace YOUR_API_KEY with the key from your dashboard:

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!"
$ch = curl_init("https://api.translateapi.ai/api/v1/translate/");
curl_setopt_array($ch, [
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_POST => true,
    CURLOPT_HTTPHEADER => [
        "Authorization: Bearer YOUR_API_KEY",
        "Content-Type: application/json"
    ],
    CURLOPT_POSTFIELDS => json_encode([
        "text" => "Hello, world!",
        "target_language" => "es"
    ])
]);

$result = json_decode(curl_exec($ch), true);
echo $result["translated_text"];  // "Hola, mundo!"
payload := strings.NewReader(`{
    "text": "Hello, world!",
    "target_language": "es"
}`)

req, _ := http.NewRequest("POST", "https://api.translateapi.ai/api/v1/translate/", payload)
req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
req.Header.Set("Content-Type", "application/json")

resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()

var result map[string]interface{}
json.NewDecoder(resp.Body).Decode(&result)
fmt.Println(result["translated_text"])  // "Hola, mundo!"
var client = new HttpClient();
client.DefaultRequestHeaders.Add("Authorization", "Bearer YOUR_API_KEY");

var content = new StringContent(
    JsonSerializer.Serialize(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 = JsonSerializer.Deserialize<JsonElement>(
    await response.Content.ReadAsStringAsync()
);
Console.WriteLine(result.GetProperty("translated_text"));  // "Hola, mundo!"
Resposta
{
    "translated_text": "Hola, mundo!",
    "source_language": "en",
    "target_language": "es",
    "translations": {
        "es": "Hola, mundo!"
    },
    "character_count": 13,
    "translation_time": 0.45
}

Autenticación

Autentique os seus pedidos empregando unha chave da API. Pode crear chaves da API desde o seu panel.

Autenticación da cabeceira (Recomendado)
Authorization: Bearer ta_your_api_key_here
ApiKey Header
Authorization: ApiKey ta_your_api_key_here
Parámetro da consulta
https://api.translateapi.ai/api/v1/translate/?api_key=ta_your_api_key_here
Manteña seguras as súas chaves da API! Non expolos no código do lado do cliente nin nos repositorios públicos.

Traducir o texto

Traducir o texto a unha única lingua de destino.

POST https://api.translateapi.ai/api/v1/translate/
Corpo da petición
Parámetros & Tipo: Requirido Descrición
text string Si Texto a traducir (máximo 50. 000 caracteres)
target_language string Si* Target language code (e.g., "es", "fr", "de")
source_language string Non Source language code. Default: "auto" (auto-detect)
engine string Non Translation engine: "auto" (default), "huggingface", or "madlad". See Translation Models. Modelos de tradución.

* Uso target_language (cadea) para unha única lingua ou target_languages (array) para múltiplos. Vexa Tradución multi- destino.

Resposta
{
    "translated_text": "Hola, mundo!",
    "source_language": "en",
    "target_language": "es",
    "translations": {
        "es": "Hola, mundo!"
    },
    "character_count": 13,
    "translation_time": 0.45
}
Auto-Detection: Omit source_language or set it to "auto" to automatically detect the source language. The detected language is returned in the source_language response field.

Tradución multi- destino

Traducir o texto a varias linguas nun só pedido. Usa o mesmo punto final que a tradución única.

POST https://api.translateapi.ai/api/v1/translate/
Corpo da petición
{
    "text": "Hello, world!",
    "target_languages": ["es", "fr", "de", "ja"],
    "source_language": "en"
}

Empregar target_languages (array) no canto de target_language (cadea) para múltiplos destinos.

Resposta
{
    "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
}
Tipo: Pode traducir a ata 50 idiomas nunha única solicitude.

Tradución por lotes

Traduza varios textos á vez con procesamento asincrónico. Envíe un lote e consulte os resultados.

Limits: Max 100 texts per batch, max 300 total items (texts × target languages). Jobs time out 45 minutes after processing starts.
Speed: Common languages (ES, FR, DE) use fast models (~0.1s/text). Less common languages use our multilingual model (~1-3s/text).
POST https://api.translateapi.ai/api/v1/translate/batch/
Paso 1: Enviar o lote
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"
}'
Resposta (HTTP 202 aceptado)
{
    "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/"
}
Paso 2: Consultar os resultados
GET https://api.translateapi.ai/api/v1/jobs/{job_id}/
Exemplo de sondaxe (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)
Resposta (completada)
{
    "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
Field Descrición
status pending (queued, waiting for a GPU worker), processing (actively translating), completed, failed
processed_texts Number of individual translations completed so far. Updates in real time as each text is translated.
progress_percentage Completion percentage (0-100). Calculated from processed_texts / total_texts.
queue_position Your position in the queue when status is "pending" (1 = next up). Null when processing or completed. Use this to estimate wait time and show queue status to your users.
processing_time Total processing time in seconds (available when completed).
Lote multilingüe

Traducir varios textos a varios idiomas á vez:

{
    "texts": ["Hello", "Goodbye"],
    "target_languages": ["es", "fr"],
    "source_language": "en"
}
Datos_ resultados completados
{
    "translations": [
        {"es": "Hola", "fr": "Bonjour"},
        {"es": "Adiós", "fr": "Au revoir"}
    ],
    "source_language": "en",
    "target_languages": ["es", "fr"],
    "character_count": 24,
    "processing_time": 2.45
}
Parámetros da petición
Parámetros & Tipo: Requirido Descrición
texts array Si Matriz de cadeas a traducir
target_language string Si* Código da lingua de destino para unha única lingua
target_languages array Si* Matriz de códigos de lingua de destino para varias linguas
source_language string Non Source language code. Default: "auto"

* Fornecer calquera target_language ou target_languages, non as dúas.

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 complete faster and give you more frequent progress updates.
  • Submit as many batch jobs as you need — our GPU cluster auto-scales to handle demand. Jobs are processed in parallel across multiple instances.
  • On timeout, re-poll the same job_id instead of submitting a new batch. The original job may still be processing on the GPU.
  • Poll every 3-5 seconds. More frequent polling does not speed up processing.

Tradución do documento

Traduza documentos enteiros preservando o formato. Soporta varios formatos de ficheiro.

POST https://api.translateapi.ai/api/v1/translate/document/
Pedido (multipart/form-data)
Parámetros & Tipo: Requirido Descrición
file file Si O documento a traducir (máx. 10MB)
target_language string Si Target language code (e.g., "es", "fr", "de")
source_language string Non Source language code. Default: "auto" (auto-detect)
Tipos de ficheiro soportados
Documents
  • .txt - Ficheiros de texto simples
  • .docx - Documentos de Word
  • .pdf - Documentos PDF (incluíndo os dixitalizados)
Data & Localization
  • .json - Ficheiros JSON (traduce valores de cadea)
  • .xml - Ficheiros XML
  • .srt - Ficheiros de subtítulos
  • .po / .pot - Ficheiros de tradución de Gettext
Images (OCR)
  • .jpg / .jpeg - Imaxes JPEG (OCR)
  • .png - Imaxes PNG (OCR)
  • .tiff / .tif - Imaxes TIFF (OCR)
  • .bmp - Imaxes BMP (OCR)
  • .webp - Imaxes WebP (OCR)
Exemplo (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"
Resposta
{
    "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"
}
Soporte de OCR: Os ficheiros de imaxe e os PDF dixitalizados son procesados co recoñecemento óptico de caracteres (OCR) para extraer o texto antes da tradución. Para obter os mellores resultados, use imaxes claras e de alta resolución.
GET https://api.translateapi.ai/api/v1/translate/document/{id}/

Comprobar o estado da tradución dun documento ou obter o URL de descarga.

Valores de estado
pending Enviouse o ficheiro, agardando a ser procesado
processing Tradución en progreso
completed Tradución completada, descarga dispoñíbel
failed Fallou a tradución (verificar a mensaxe_ de_ erro)

Idiomas soportados

Obtén a lista de todas as linguas soportadas.

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

View All 186 Languages

Submit Corrections

Suggest a better translation for a given source text. Corrections enter a moderation queue; once approved by our team they surface as "Community Verified" translations for that text.

Note: this endpoint is served from the main domain https://translateapi.ai/api/v1/ (not the api. translation host), and requires an API key.
POST https://translateapi.ai/api/v1/suggestions/
Corpo da petición
Parameter & Tipo: Descrición
source_text string The original text that was translated.
source_language string Source language code (e.g. "en").
target_language string Target language code (e.g. "es").
machine_translation string The machine translation you are correcting.
suggested_translation string Your improved translation (must differ from machine_translation).
Example Request
curl -X POST https://translateapi.ai/api/v1/suggestions/ \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
    "source_text": "Hello, world!",
    "source_language": "en",
    "target_language": "es",
    "machine_translation": "Hola, mundo!",
    "suggested_translation": "¡Hola, mundo!"
}'
Resposta
{
    "id": 4213,
    "status": "pending",
    "created": true,
    "message": "Correction submitted for review."
}

Re-submitting the same source/language pair updates your existing suggestion instead of creating a duplicate (returns 200 with "created": false).

Modelos de tradución

Usamos modelos de tradución de código aberto de última xeración que se executan na nosa propia infraestrutura de GPU. Todos os modelos teñen licenza comercial (Apache 2. 0).

Modelo Linguas Mellor para
Helsinki-NLP/opus-mt Máis de 50 parellas de linguas Linguas comúns (EN, ES, FR, DE, IT, PT, RU, ZH, JA, etc.)
Google MADLAD-400 Máis de 400 idiomas Linguas raras, cobertura completa

A API selecciona automaticamente o mellor modelo para o seu par de linguas. Opcionalmente pode especificar un engine parámetro:

Motor Descrición
"auto" Por omisión. Tenta HuggingFace primeiro, volve a MADLAD- 400
"huggingface" Forzar HuggingFace/MarianMT (máis rápido, máis de 50 linguas)
"madlad" Force MADLAD-400 (máis de 400 linguas)

Xestión de erros

A API usa códigos de estado HTTP estándar para indicar éxito ou fracaso.

Código Descrición
200 Éxito
202 Accepted — Batch job queued successfully
400 Bad Request — Invalid parameters (missing text, unsupported language, etc.)
401 Non autorizado - Falta a chave da API ou non é válida
402 Payment Required — Character credits exhausted. Upgrade your plan or purchase a top-up.
403 Forbidden — API key lacks required scope or IP not in whitelist
503 O servizo non está dispoñíbel - O motor de tradución está temporalmente parado
Formato da resposta de erro
{
    "error": "insufficient_credits",
    "credits_remaining": 0
}

Usage Limits

TranslateAPI has no request rate limits. All requests are queued and processed by our auto-scaling GPU cluster. Your plan determines your monthly character allowance:

Plano Caracteres/ Mes Batch API Documents Prezo
Libre 250,000 — — $0 Inscríbete gratis
Iniciador 2,500,000 $9/ms Subscribirse
Pro 10,000,000 $29/ms Subscribirse
Negocios 40,000,000 $79/ms Subscribirse
Escala 125,000,000 $199/ms Subscribirse
Enterprise Unlimited $499/ms Contact Sales

Cando exceda o seu límite, recibirá un 402 Payment Required Non recibirá ningunha resposta ata o próximo mes ou que actualice.

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. All requests are queued and processed — send hundreds of concurrent requests and they'll all be handled. Real-time translations get priority, batch jobs process in the background.

Need More Credits?

Run out of characters mid-month? Purchase a one-time credit top-up without changing your plan. View top-up packs

Cualificar esta páxina
Grazas pola túa valoración!
/5 baseado en valoracións