openapi: 3.2.0
info:
  description: The LocalAI Rest API.
  title: LocalAI Video API
  contact:
    name: LocalAI
    url: https://localai.io
  license:
    name: MIT
    url: https://raw.githubusercontent.com/mudler/LocalAI/master/LICENSE
  version: 2.0.0
servers:
- url: /
tags:
- name: video
paths:
  /video:
    post:
      tags:
      - video
      summary: Creates a video from a prompt and optional image or audio conditioning.
      responses:
        '200':
          description: Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/schema.OpenAIResponse'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/schema.VideoRequest'
        description: query params
        required: true
components:
  schemas:
    schema.InputTokensDetails:
      type: object
      properties:
        image_tokens:
          type: integer
        text_tokens:
          type: integer
    schema.Choice:
      type: object
      properties:
        delta:
          $ref: '#/components/schemas/schema.Message'
        finish_reason:
          type: string
        index:
          type: integer
        logprobs:
          $ref: '#/components/schemas/schema.Logprobs'
        message:
          $ref: '#/components/schemas/schema.Message'
        text:
          type: string
    schema.ToolCall:
      type: object
      properties:
        function:
          $ref: '#/components/schemas/schema.FunctionCall'
        id:
          type: string
        index:
          type: integer
        type:
          type: string
    schema.Message:
      type: object
      properties:
        content:
          description: The message content
        function_call:
          description: A result of a function call
        name:
          description: The message name (used for tools calls)
          type: string
        reasoning:
          description: Reasoning content extracted from <thinking>...</thinking> tags
          type: string
        role:
          description: The message role
          type: string
        tool_call_id:
          type: string
        tool_calls:
          type: array
          items:
            $ref: '#/components/schemas/schema.ToolCall'
    schema.LogprobContent:
      type: object
      properties:
        bytes:
          type: array
          items:
            type: integer
        id:
          type: integer
        logprob:
          type: number
        token:
          type: string
        top_logprobs:
          type: array
          items:
            $ref: '#/components/schemas/schema.LogprobContent'
    schema.Item:
      type: object
      properties:
        b64_json:
          type: string
        index:
          type: integer
        object:
          type: string
        url:
          description: Images
          type: string
    schema.OpenAIUsage:
      type: object
      properties:
        completion_tokens:
          type: integer
        compression_meta:
          $ref: '#/components/schemas/schema.CompressionMetadata'
        input_tokens:
          description: Fields for image generation API compatibility
          type: integer
        input_tokens_details:
          $ref: '#/components/schemas/schema.InputTokensDetails'
        output_tokens:
          type: integer
        prompt_tokens:
          type: integer
        timing_prompt_processing:
          description: Extra timing data, disabled by default as is't not a part of OpenAI specification
          type: number
        timing_token_generation:
          type: number
        total_tokens:
          type: integer
    schema.VideoRequest:
      type: object
      properties:
        audio:
          description: URL or base64 audio for audio-conditioned generation
          type: string
        cfg_scale:
          description: classifier-free guidance scale
          type: number
        end_image:
          description: URL or base64 of the last frame
          type: string
        fps:
          description: frames per second
          type: integer
        height:
          description: output height in pixels
          type: integer
        input_reference:
          description: reference image or video URL
          type: string
        model:
          type: string
        negative_prompt:
          description: things to avoid in the output
          type: string
        num_frames:
          description: total number of frames to generate
          type: integer
        params:
          description: backend-specific generation parameters
          type: object
          additionalProperties:
            type: string
        prompt:
          description: text description of the video to generate
          type: string
        response_format:
          description: output format (url or b64_json)
          type: string
        seconds:
          description: duration in seconds (alternative to num_frames)
          type: string
        seed:
          description: random seed for reproducibility
          type: integer
        size:
          description: WxH shorthand (e.g. "512x512")
          type: string
        start_image:
          description: URL or base64 of the first frame
          type: string
        step:
          description: number of diffusion steps
          type: integer
        width:
          description: output width in pixels
          type: integer
    schema.OpenAIResponse:
      type: object
      properties:
        choices:
          type: array
          items:
            $ref: '#/components/schemas/schema.Choice'
        created:
          type: integer
        data:
          type: array
          items:
            $ref: '#/components/schemas/schema.Item'
        id:
          type: string
        model:
          type: string
        object:
          type: string
        usage:
          description: 'Usage is intentionally a pointer with omitempty: per the OpenAI

            chat-completion streaming spec, intermediate chunks must not carry

            a `usage` field. Marshalling a value-typed usage would emit

            `"usage":{"prompt_tokens":0,...}` on every chunk and break

            OpenAI-SDK consumers that filter on a truthy `result.usage`

            (continuedev/continue, Kilo Code, Roo Code, etc.).'
          allOf:
          - $ref: '#/components/schemas/schema.OpenAIUsage'
    schema.FunctionCall:
      type: object
      properties:
        arguments:
          type: string
        name:
          type: string
    schema.Logprobs:
      type: object
      properties:
        content:
          type: array
          items:
            $ref: '#/components/schemas/schema.LogprobContent'
    schema.CompressionMetadata:
      type: object
      properties:
        compressed_tokens:
          type: integer
        compressor:
          type: string
        dropped_turns:
          type: integer
        original_tokens:
          type: integer
        overflow_recoveries:
          type: integer
        summary_tokens:
          type: integer
  securitySchemes:
    BearerAuth:
      type: apiKey
      name: Authorization
      in: header