> ## Documentation Index
> Fetch the complete documentation index at: https://www.vozo.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Visual Translate Job

> Create a visual translation job for video on-screen text



## OpenAPI

````yaml POST /v1/media/frame_translate
openapi: 3.1.0
info:
  title: Vozo API
  description: API for Generating, Editing and Localizing Talking Videos.
  license:
    name: MIT
  version: 1.0.0
servers:
  - url: https://api.vozo.ai
security:
  - bearerAuth: []
paths:
  /v1/media/frame_translate:
    post:
      description: Create a visual translation job for video on-screen text
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VisualTranslateRequest'
      responses:
        '200':
          description: Job queued
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VisualTranslateJobQueue'
        '400':
          description: unexpected error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  schemas:
    VisualTranslateRequest:
      type: object
      required:
        - video_url
        - source_language
        - target_language
      properties:
        video_url:
          type: string
          description: >-
            Publicly accessible URL of the input video for the server to
            download. Maximum supported input duration is 20 minutes.
        source_language:
          type: string
          description: >-
            Source language code. Auto detection is not supported; pass a
            supported language code such as en-US or zh-CN.
          pattern: ^[a-z]{2,3}(-[A-Za-z0-9]+)*$
        target_language:
          type: string
          description: >-
            Target language code. Locale is optional and may include regional
            variants, e.g. en, en-US, zh, zh-CN, zh-CN-GUANGXI. Only the
            language part is validated against the supported list.
          pattern: ^[a-z]{2,3}(-[A-Za-z0-9]+)*$
        glossary_ids:
          type: array
          description: >-
            List of glossary IDs from the product. Up to 3 glossaries can be
            applied during translation for consistent terminology.
          maxItems: 3
          items:
            type: string
        user_prompt:
          type: string
          description: Optional prompt to guide visual text translation style.
        project_mode:
          $ref: '#/components/schemas/ProjectMode'
          description: >-
            Controls project creation behavior in the web dashboard. editable
            creates an editable visual translation project; none disables
            project creation.
        callback_url:
          type: string
          description: Webhook callback URL for status changes.
    VisualTranslateJobQueue:
      type: object
      required:
        - task_id
      properties:
        task_id:
          type: string
          description: ID of the visual translation task.
    Error:
      required:
        - code
        - message
      type: object
      properties:
        code:
          type: string
        message:
          type: string
        serverTs:
          type: string
    ProjectMode:
      type: string
      enum:
        - none
        - editable
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: APIKey
      description: >-
        Bearer authentication header of the form Bearer <api_key>, where
        <api_key> is your API Key. The token in the sample code is referring to
        this api_key as well.

````