Kling AI Lip-Sync API

openapi: 3.0.3
info:
  title: Kling AI Open Platform API
  description: >-
    The Kling AI Open Platform is the developer API for Kuaishou's Kling
    generative video and image models. Every capability follows the same
    asynchronous pattern: submit a task with POST (receiving a task_id), then
    poll the matching GET endpoint by task_id until status is succeed and the
    generated video or image URLs are returned. Generated asset URLs are
    short-lived and should be downloaded promptly. Authentication uses a JWT
    (HS256) signed from an Access Key / Secret Key pair, passed as a Bearer
    token; tokens are short-lived (about 30 minutes).


    endpointsModeled: The overall path structure, async task model, JWT auth,
    and model catalog are grounded in Kling's official Open Platform
    documentation and cross-referenced against multiple Kling API wrappers.
    Kling's official reference pages block automated fetching (HTTP 446), so
    exact request/response field-level schemas here are honestly modeled on the
    documented behavior rather than copied verbatim, and should be reconciled
    against the live reference before code generation.
  version: '1.0'
  contact:
    name: Kling AI Open Platform
    url: https://app.klingai.com/global/dev
servers:
  - url: https://api.klingai.com
    description: Kling AI Open Platform (global)
security:
  - bearerAuth: []
tags:
  - name: Text-to-Video
    description: Generate video from a text prompt.
  - name: Image-to-Video
    description: Animate images into video.
  - name: Video Extension
    description: Extend an existing generated video.
  - name: Lip-Sync
    description: Sync a subject's lips to speech or audio.
  - name: Video Effects
    description: Apply preset creative effects to images.
  - name: Image Generation
    description: Generate still images with the Kolors models.
  - name: Virtual Try-On
    description: Composite a garment onto a person image.
  - name: Account
    description: Resource-pack balance and consumption.
paths:
  /v1/videos/text2video:
    post:
      operationId: createTextToVideoTask
      tags:
        - Text-to-Video
      summary: Create a text-to-video task
      description: Submit a text prompt to generate a video. Returns a task_id to poll.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/TextToVideoRequest'
      responses:
        '200':
          description: Task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreatedResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/RateLimited'
  /v1/videos/text2video/{task_id}:
    get:
      operationId: getTextToVideoTask
      tags:
        - Text-to-Video
      summary: Query a text-to-video task
      parameters:
        - $ref: '#/components/parameters/TaskId'
      responses:
        '200':
          description: Task status and, when complete, the generated video URL.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoTaskResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
  /v1/videos/image2video:
    post:
      operationId: createImageToVideoTask
      tags:
        - Image-to-Video
      summary: Create an image-to-video task
      description: Animate a start image (and optional end image) with a motion prompt.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ImageToVideoRequest'
      responses:
        '200':
          description: Task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreatedResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '429':
          $ref: '#/components/responses/RateLimited'
  /v1/videos/image2video/{task_id}:
    get:
      operationId: getImageToVideoTask
      tags:
        - Image-to-Video
      summary: Query an image-to-video task
      parameters:
        - $ref: '#/components/parameters/TaskId'
      responses:
        '200':
          description: Task status and, when complete, the generated video URL.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoTaskResponse'
  /v1/videos/multi-image2video:
    post:
      operationId: createMultiImageToVideoTask
      tags:
        - Image-to-Video
      summary: Create a multi-image-to-video task
      description: Compose a video from multiple reference images plus a prompt.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/MultiImageToVideoRequest'
      responses:
        '200':
          description: Task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreatedResponse'
  /v1/videos/multi-image2video/{task_id}:
    get:
      operationId: getMultiImageToVideoTask
      tags:
        - Image-to-Video
      summary: Query a multi-image-to-video task
      parameters:
        - $ref: '#/components/parameters/TaskId'
      responses:
        '200':
          description: Task status and, when complete, the generated video URL.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoTaskResponse'
  /v1/videos/video-extend:
    post:
      operationId: createVideoExtendTask
      tags:
        - Video Extension
      summary: Create a video-extension task
      description: Extend an existing generated video by its origin task id.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VideoExtendRequest'
      responses:
        '200':
          description: Task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreatedResponse'
  /v1/videos/video-extend/{task_id}:
    get:
      operationId: getVideoExtendTask
      tags:
        - Video Extension
      summary: Query a video-extension task
      parameters:
        - $ref: '#/components/parameters/TaskId'
      responses:
        '200':
          description: Task status and, when complete, the extended video URL.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoTaskResponse'
  /v1/videos/lip-sync:
    post:
      operationId: createLipSyncTask
      tags:
        - Lip-Sync
      summary: Create a lip-sync task
      description: Sync a video subject's lips to supplied text (TTS) or an audio file.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/LipSyncRequest'
      responses:
        '200':
          description: Task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreatedResponse'
  /v1/videos/lip-sync/{task_id}:
    get:
      operationId: getLipSyncTask
      tags:
        - Lip-Sync
      summary: Query a lip-sync task
      parameters:
        - $ref: '#/components/parameters/TaskId'
      responses:
        '200':
          description: Task status and, when complete, the lip-synced video URL.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoTaskResponse'
  /v1/videos/effects:
    post:
      operationId: createVideoEffectsTask
      tags:
        - Video Effects
      summary: Create a video-effects task
      description: Apply a preset creative effect to one or more input images.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VideoEffectsRequest'
      responses:
        '200':
          description: Task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreatedResponse'
  /v1/videos/effects/{task_id}:
    get:
      operationId: getVideoEffectsTask
      tags:
        - Video Effects
      summary: Query a video-effects task
      parameters:
        - $ref: '#/components/parameters/TaskId'
      responses:
        '200':
          description: Task status and, when complete, the effect video URL.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VideoTaskResponse'
  /v1/images/generations:
    post:
      operationId: createImageGenerationTask
      tags:
        - Image Generation
      summary: Create an image-generation task
      description: Generate still images from a text prompt with the Kolors models.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ImageGenerationRequest'
      responses:
        '200':
          description: Task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreatedResponse'
  /v1/images/generations/{task_id}:
    get:
      operationId: getImageGenerationTask
      tags:
        - Image Generation
      summary: Query an image-generation task
      parameters:
        - $ref: '#/components/parameters/TaskId'
      responses:
        '200':
          description: Task status and, when complete, the generated image URLs.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ImageTaskResponse'
  /v1/images/kolors-virtual-try-on:
    post:
      operationId: createVirtualTryOnTask
      tags:
        - Virtual Try-On
      summary: Create a virtual try-on task
      description: Composite a garment image onto a person/model image.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VirtualTryOnRequest'
      responses:
        '200':
          description: Task accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TaskCreatedResponse'
  /v1/images/kolors-virtual-try-on/{task_id}:
    get:
      operationId: getVirtualTryOnTask
      tags:
        - Virtual Try-On
      summary: Query a virtual try-on task
      parameters:
        - $ref: '#/components/parameters/TaskId'
      responses:
        '200':
          description: Task status and, when complete, the try-on image URLs.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ImageTaskResponse'
  /account/costs:
    get:
      operationId: getAccountResourcePacks
      tags:
        - Account
      summary: Query resource-pack balances
      description: Return remaining prepaid resource-pack balances and consumption.
      parameters:
        - name: start_time
          in: query
          required: false
          schema:
            type: integer
          description: Start of the query window as a Unix millisecond timestamp.
        - name: end_time
          in: query
          required: false
          schema:
            type: integer
          description: End of the query window as a Unix millisecond timestamp.
      responses:
        '200':
          description: Resource-pack balance and consumption detail.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AccountCostsResponse'
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: >-
        A JWT signed with HS256 from your Access Key (as the iss claim) and
        Secret Key, passed as Authorization: Bearer <token>. Tokens are
        short-lived (about 30 minutes; nbf is typically set 5 seconds in the
        past).
  parameters:
    TaskId:
      name: task_id
      in: path
      required: true
      schema:
        type: string
      description: The task identifier returned by the create-task call.
  responses:
    Unauthorized:
      description: Missing, invalid, or expired JWT.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
    RateLimited:
      description: Too many requests or concurrency limit exceeded.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  schemas:
    TextToVideoRequest:
      type: object
      required:
        - prompt
      properties:
        model_name:
          type: string
          description: Video model, e.g. kling-v1, kling-v1-6, kling-v2-master, kling-v2-1, kling-v2-5-turbo, kling-v2-6.
          example: kling-v2-6
        prompt:
          type: string
          description: Text description of the video to generate.
        negative_prompt:
          type: string
          description: Content to avoid.
        cfg_scale:
          type: number
          description: Prompt adherence strength, 0 to 1.
        mode:
          type: string
          enum:
            - std
            - pro
          description: Standard or professional generation mode.
        aspect_ratio:
          type: string
          enum:
            - '16:9'
            - '9:16'
            - '1:1'
          description: Output aspect ratio.
        duration:
          type: string
          enum:
            - '5'
            - '10'
          description: Video length in seconds.
        callback_url:
          type: string
          description: Optional URL notified when the task completes.
    ImageToVideoRequest:
      type: object
      required:
        - image
      properties:
        model_name:
          type: string
          example: kling-v2-6
        image:
          type: string
          description: Start-frame image as a URL or base64 string.
        image_tail:
          type: string
          description: Optional end-frame image as a URL or base64 string.
        prompt:
          type: string
        negative_prompt:
          type: string
        cfg_scale:
          type: number
        mode:
          type: string
          enum:
            - std
            - pro
        duration:
          type: string
          enum:
            - '5'
            - '10'
        callback_url:
          type: string
    MultiImageToVideoRequest:
      type: object
      required:
        - image_list
        - prompt
      properties:
        model_name:
          type: string
          example: kling-v1-6
        image_list:
          type: array
          items:
            type: string
          description: List of reference image URLs or base64 strings.
        prompt:
          type: string
        mode:
          type: string
          enum:
            - std
            - pro
        duration:
          type: string
          enum:
            - '5'
            - '10'
        callback_url:
          type: string
    VideoExtendRequest:
      type: object
      required:
        - video_id
      properties:
        video_id:
          type: string
          description: The origin task/video id of a previously generated video to extend.
        prompt:
          type: string
          description: Optional continuation prompt.
        callback_url:
          type: string
    LipSyncRequest:
      type: object
      properties:
        video_id:
          type: string
          description: Origin task/video id of the video to lip-sync.
        video_url:
          type: string
          description: Alternatively, a URL to the source video.
        mode:
          type: string
          enum:
            - text2video
            - audio2video
          description: Drive lips from generated speech (text) or from an audio file.
        text:
          type: string
          description: Text to synthesize into speech when mode is text2video.
        voice_id:
          type: string
          description: Voice identifier for text-to-speech.
        audio_url:
          type: string
          description: Audio file URL when mode is audio2video.
        callback_url:
          type: string
    VideoEffectsRequest:
      type: object
      required:
        - effect_scene
      properties:
        effect_scene:
          type: string
          description: Preset effect name, e.g. hug, kiss, squish, expansion.
        model_name:
          type: string
          example: kling-v1-6
        image:
          type: string
          description: Input image URL or base64 string.
        images:
          type: array
          items:
            type: string
          description: Multiple input images for effects that require them.
        duration:
          type: string
          enum:
            - '5'
        callback_url:
          type: string
    ImageGenerationRequest:
      type: object
      required:
        - prompt
      properties:
        model_name:
          type: string
          description: Image model, e.g. kling-v1, kling-v1-5, kling-v2, kling-v2-1.
          example: kling-v2-1
        prompt:
          type: string
        negative_prompt:
          type: string
        image:
          type: string
          description: Optional reference image URL or base64 string.
        image_reference:
          type: string
          enum:
            - subject
            - face
          description: How the reference image is used.
        n:
          type: integer
          description: Number of images to generate.
        aspect_ratio:
          type: string
          enum:
            - '16:9'
            - '9:16'
            - '1:1'
            - '4:3'
            - '3:4'
        callback_url:
          type: string
    VirtualTryOnRequest:
      type: object
      required:
        - human_image
        - cloth_image
      properties:
        model_name:
          type: string
          example: kolors-virtual-try-on-v1-5
        human_image:
          type: string
          description: Person/model image URL or base64 string.
        cloth_image:
          type: string
          description: Garment image URL or base64 string.
        callback_url:
          type: string
    TaskCreatedResponse:
      type: object
      properties:
        code:
          type: integer
          description: Business status code (0 indicates success).
        message:
          type: string
        request_id:
          type: string
        data:
          type: object
          properties:
            task_id:
              type: string
            task_status:
              type: string
              enum:
                - submitted
                - processing
                - succeed
                - failed
            created_at:
              type: integer
            updated_at:
              type: integer
    VideoTaskResponse:
      type: object
      properties:
        code:
          type: integer
        message:
          type: string
        request_id:
          type: string
        data:
          type: object
          properties:
            task_id:
              type: string
            task_status:
              type: string
              enum:
                - submitted
                - processing
                - succeed
                - failed
            task_result:
              type: object
              properties:
                videos:
                  type: array
                  items:
                    type: object
                    properties:
                      id:
                        type: string
                      url:
                        type: string
                      duration:
                        type: string
    ImageTaskResponse:
      type: object
      properties:
        code:
          type: integer
        message:
          type: string
        request_id:
          type: string
        data:
          type: object
          properties:
            task_id:
              type: string
            task_status:
              type: string
              enum:
                - submitted
                - processing
                - succeed
                - failed
            task_result:
              type: object
              properties:
                images:
                  type: array
                  items:
                    type: object
                    properties:
                      index:
                        type: integer
                      url:
                        type: string
    AccountCostsResponse:
      type: object
      properties:
        code:
          type: integer
        message:
          type: string
        data:
          type: object
          properties:
            resource_pack_subscribe_infos:
              type: array
              items:
                type: object
                properties:
                  resource_pack_name:
                    type: string
                  resource_pack_type:
                    type: string
                  total_quantity:
                    type: number
                  remaining_quantity:
                    type: number
                  status:
                    type: string
    Error:
      type: object
      properties:
        code:
          type: integer
        message:
          type: string
        request_id:
          type: string