BRASILTradução de apoio para consulta. Código e identificadores técnicos preservados. Consultar referência original ↗
Criar tarefa de tradução de imagens
Envie um qwen-mt-image tarefa de tradução de imagem assíncrona
OpenAPI
openapi: 3.0.0
info:
title: Qwen-MT-Image API Reference
description: |-
Qwen-MT-Image accurately translates text in images while preserving the original layout. It supports domain hints, sensitive word filtering, and terminology intervention.
`qwen-mt-image-2.0` supports both synchronous and asynchronous modes. See [Synchronous calls](/api-reference/image-translation/qwen-mt-image/synchronous) for the sync API.
Asynchronous workflow:
1. **Create task**: POST to submit a task and receive a task_id.
2. **Query result**: Poll by task_id until the task completes and returns the image URL.
version: 1.0.0
servers:
- url: https://maas.qwencloudapi.com/api/v1
description: DashScope International API
security:
- BearerAuth: []
paths:
/services/aigc/image2image/image-synthesis:
post:
operationId: createImageTranslationTask
summary: Create image translation task
description: Create an asynchronous image translation task. The image must contain text in a supported language.
parameters:
- name: X-DashScope-Async
in: header
required: true
description: |-
Async processing flag. Must be set to `enable` for async calls.
`qwen-mt-image-2.0` supports [synchronous calls](/api-reference/image-translation/qwen-mt-image/synchronous) — omit this header for sync mode. `qwen-mt-image` only supports async.
schema:
type: string
enum:
- enable
requestBody:
required: true
content:
application/json:
schema:
$ref: "#/components/schemas/ImageTranslationRequest"
responses:
"200":
description: Task created successfully. Returns task_id for polling.
content:
application/json:
schema:
$ref: "#/components/schemas/AsyncTaskSubmitResponse"
"400":
description: Invalid request parameters.
content:
application/json:
schema:
$ref: "#/components/schemas/DashScopeErrorResponse"
x-codeSamples:
- lang: curl
label: cURL
source: |-
curl --location 'https://maas.qwencloudapi.com/api/v1/services/aigc/image2image/image-synthesis' \
--header 'X-DashScope-Async: enable' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
"model": "qwen-mt-image",
"input": {
"image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250916/ordhsk/1.webp",
"source_lang": "zh",
"target_lang": "en",
"ext": {
"config": {
"imageSegment": false
}
}
}
}'
components:
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: Qwen Cloud API Key. See [Get API Key](/api-reference/preparation/api-key).
schemas:
ImageTranslationRequest:
type: object
description: Image translation request body.
required:
- model
- input
properties:
model:
type: string
enum:
- qwen-mt-image
description: "Model name: `qwen-mt-image-2.0` or `qwen-mt-image`."
input:
type: object
description: Input parameters.
required:
- image_url
- source_lang
- target_lang
properties:
image_url:
type: string
description: |-
Public URL of the image (HTTP/HTTPS).
- **Formats**: JPG, JPEG, PNG, BMP, PNM, PPM, TIFF, WEBP
- **Dimensions**: 15-8192px width/height, aspect ratio 1:10 to 10:1
- **Size**: max 100MB
- URL must not contain Chinese characters
source_lang:
type: string
description: |-
Source language. Accepts full name, language code, or `auto` (auto-detect), case-insensitive.
**qwen-mt-image-2.0**: supports 55 languages with no restrictions. See [Supported languages](/api-reference/image-translation/qwen-mt-image/synchronous#supported-languages).
**qwen-mt-image** (legacy): source or target must be Chinese or English. Supported: `zh`, `en`, `ko`, `ja`, `ru`, `es`, `fr`, `pt`, `it`, `vi`, `de`.
Example: `Chinese`, `en`, `auto`
target_lang:
type: string
description: |-
Target language. Accepts full name or language code, case-insensitive.
**qwen-mt-image-2.0**: supports 55 languages with no restrictions. See [Supported languages](/api-reference/image-translation/qwen-mt-image/synchronous#supported-languages).
**qwen-mt-image** (legacy): source or target must be Chinese or English. Supported: `zh`, `en`, `ko`, `ja`, `ru`, `es`, `fr`, `pt`, `it`, `vi`, `ms`, `th`, `id`, `ar`. Note: German (`de`) is source-only.
Example: `Chinese`, `en`
ext:
type: object
description: Optional extension parameters.
properties:
domainHint:
type: string
description: Domain hint in English describing the translation context and style requirements. Max 200 words.
sensitives:
type: array
description: |-
Sensitive words list — exact matches are skipped during translation, case-sensitive. Max 50 per request.
Example: ["SALE", "Limited Time"]
items:
type: string
maxItems: 50
terminologies:
type: array
description: |-
Terminology pairs for domain-specific translation. Language must match `source_lang` and `target_lang`.
Example: [{"src": "API", "tgt": "API"}, {"src": "ML", "tgt": "ML"}]
items:
type: object
required:
- src
- tgt
properties:
src:
type: string
description: Source term, must match `source_lang`.
tgt:
type: string
description: Target term, must match `target_lang`.
config:
type: object
description: Additional configuration options.
properties:
imageSegment:
type: boolean
default: false
description: |-
Enable image subject segmentation. When enabled, text on subjects (people, products, logos) is not translated.
- `false` (default): translate all text
- `true`: skip text on subjects
AsyncTaskSubmitResponse:
type: object
description: Async task submission response.
properties:
request_id:
type: string
description: Unique request identifier for tracing and troubleshooting.
output:
type: object
description: Task output.
properties:
task_id:
type: string
description: Task ID. Valid for 24 hours.
task_status:
type: string
enum:
- PENDING
description: Task status. Newly created tasks always return `PENDING`.
ImageTranslationTaskStatusResponse:
type: object
description: Task status and result response.
properties:
request_id:
type: string
description: Unique request identifier for tracing and troubleshooting.
output:
type: object
description: Task output.
properties:
task_id:
type: string
description: Task ID. Valid for 24 hours.
task_status:
type: string
enum:
- PENDING
- RUNNING
- SUCCEEDED
- FAILED
- CANCELED
- UNKNOWN
description: |-
Task status.
- PENDING: task is queued
- RUNNING: task is processing
- SUCCEEDED: task completed successfully
- FAILED: task failed
- CANCELED: task was canceled
- UNKNOWN: task does not exist or status is unknown
submit_time:
type: string
description: "Task submission time. Format: YYYY-MM-DD HH:mm:ss.SSS."
scheduled_time:
type: string
description: "Task execution start time. Format: YYYY-MM-DD HH:mm:ss.SSS."
end_time:
type: string
description: "Task completion time. Format: YYYY-MM-DD HH:mm:ss.SSS."
image_url:
type: string
description: URL of the translated image, same dimensions as the original, JPG format. Valid for 24 hours — download and save promptly.
message:
type: string
description: Additional information. Usually not returned. When the image contains no translatable text, the task still succeeds (and is billed), returning `No text detected for translation`. On failure, contains error details.
code:
type: string
description: Error code. Not returned on success.
usage:
type: object
description: Usage statistics. Only counts successful results.
properties:
image_count:
type: integer
description: Number of images generated, always 1.
DashScopeErrorResponse:
type: object
description: DashScope API error response.
properties:
code:
type: string
description: Error code (e.g. `InvalidApiKey`, `InvalidParameter`).
message:
type: string
description: Human-readable error description.
request_id:
type: string
description: Unique request identifier.