> ## Documentation Index > Fetch the complete documentation index at: https://docs.skills.video/llms.txt > Use this file to discover all available pages before exploring further. # Kling O3 Video Upto 15s, with video or image references, audio-backed. ## OpenAPI ````yaml /openapi.json post /generation/kling-ai/o3/video openapi: 3.1.0 info: title: skills.video OpenAPI version: 1.0.0 description: OpenAPI schema for skills.video API endpoints. servers: - url: https://open.skills.video/api/v1 security: [] paths: /generation/kling-ai/o3/video: post: summary: Kling O3 Video requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/kling_ai_o3_videoCreateRequest' multipart/form-data: schema: $ref: '#/components/schemas/kling_ai_o3_videoMultipartCreateRequest' responses: '200': description: Generation submission accepted content: application/json: example: id: gen_123 status: IN_QUEUE input: prompt: a cat walking through neon rain duration: 5 aspect_ratio: '16:9' 'n': 1 usage: total: 20 subscription: 20 permanent: 0 schema: $ref: '#/components/schemas/kling_ai_o3_videoPrediction' '400': description: >- Video generation request was rejected as invalid or model is not supported. content: application/json: example: error: VIDEO_GENERATION_INVALID_INPUT code: VIDEO_GENERATION_INVALID_INPUT message: '''prompt'' parameter is required' schema: anyOf: - $ref: '#/components/schemas/VideoGenerationErrorResponse' - $ref: '#/components/schemas/TemplateErrorResponse' - $ref: '#/components/schemas/ErrorResponse' '401': description: Authentication required or failed content: application/json: example: error: UNAUTHORIZED code: UNAUTHORIZED message: Unauthorized schema: $ref: '#/components/schemas/ErrorResponse' '402': description: Workspace does not have enough credits to run this generation. content: application/json: example: error: INSUFFICIENT_CREDITS code: VIDEO_GENERATION_INSUFFICIENT_CREDITS message: Insufficient credits for this generation. schema: $ref: '#/components/schemas/VideoGenerationErrorResponse' '403': description: Workspace access is forbidden or Seedance verification is required. content: application/json: example: error: WORKSPACE_FORBIDDEN code: WORKSPACE_FORBIDDEN message: You do not have access to this workspace. schema: anyOf: - $ref: '#/components/schemas/ErrorResponse' - $ref: '#/components/schemas/SeedanceVerificationErrorResponse' '404': description: Resource, model, or template not found. content: application/json: example: error: TEMPLATE_NOT_FOUND code: TEMPLATE_NOT_FOUND message: Template not found. schema: anyOf: - $ref: '#/components/schemas/ErrorResponse' - $ref: '#/components/schemas/TemplateErrorResponse' '422': description: Upstream moderation rejected the request content. content: application/json: example: error: VIDEO_GENERATION_CONTENT_REJECTED code: VIDEO_GENERATION_CONTENT_REJECTED message: Request content was rejected by the moderation policy. schema: $ref: '#/components/schemas/VideoGenerationErrorResponse' '429': description: Generation rate limit exceeded upstream. content: application/json: example: error: VIDEO_GENERATION_RATE_LIMITED code: VIDEO_GENERATION_RATE_LIMITED message: Rate limit exceeded. Please retry later. schema: $ref: '#/components/schemas/VideoGenerationErrorResponse' '500': description: >- Video generation failed before provider execution completed. Response includes code and message fields. content: application/json: example: error: VIDEO_GENERATION_FAILED code: VIDEO_GENERATION_FAILED message: Generation failed. schema: anyOf: - $ref: '#/components/schemas/VideoGenerationErrorResponse' - $ref: '#/components/schemas/ErrorResponse' '502': description: >- Video generation failed. Returned when the upstream provider reports a generic failure. content: application/json: example: error: VIDEO_GENERATION_FAILED code: VIDEO_GENERATION_FAILED message: Generation failed. schema: $ref: '#/components/schemas/VideoGenerationErrorResponse' '503': description: Upstream generation provider is unavailable. content: application/json: example: error: VIDEO_GENERATION_PROVIDER_UNAVAILABLE code: VIDEO_GENERATION_PROVIDER_UNAVAILABLE message: Upstream generation provider is temporarily unavailable. schema: $ref: '#/components/schemas/VideoGenerationErrorResponse' '504': description: Video generation exceeded the upstream timeout. content: application/json: example: error: VIDEO_GENERATION_TIMEOUT code: VIDEO_GENERATION_TIMEOUT message: Generation timed out. schema: $ref: '#/components/schemas/VideoGenerationErrorResponse' security: - bearerAuth: [] components: schemas: kling_ai_o3_videoCreateRequest: $ref: '#/components/schemas/kling_ai_o3_videoInput' title: Input xMeta: video_duration: video_url kling_ai_o3_videoMultipartCreateRequest: title: Input xMeta: video_duration: video_url allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature default: text-image-to-video type: string enum: - text-image-to-video - frame-to-video - reference-to-video - video-to-video - video-reference-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: >- Start frame image URL for image-to-video. When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. title: Image x-cli-aliases: - image anyOf: - format: uri type: string - format: binary type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. title: Start Image x-cli-aliases: - start-image anyOf: - format: uri type: string - format: binary type: string end_image_url: description: >- End frame image URL for image-to-video / reference-to-video. When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. title: End Image x-cli-aliases: - end-image anyOf: - format: uri type: string - format: binary type: string first_frame_url: description: >- First frame image URL for frame-to-video mode. When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. title: First Frame x-cli-aliases: - first-frame - start-frame anyOf: - format: uri type: string - format: binary type: string last_frame_url: description: >- Optional last frame image URL for frame-to-video mode. When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. title: Last Frame x-cli-aliases: - last-frame - end-frame anyOf: - format: uri type: string - format: binary type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 x-cli-aliases: - image - images anyOf: - maxItems: 4 type: array items: description: >- When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. anyOf: - format: uri type: string - format: binary type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 x-cli-aliases: - reference-image - reference-images anyOf: - maxItems: 4 type: array items: description: >- When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. anyOf: - format: uri type: string - format: binary type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. title: Video xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 x-cli-aliases: - video anyOf: - format: uri type: string - format: binary type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - anyOf: - title: Text/Image type: object properties: feature: type: string enum: - text-image-to-video image_url: x-cli-aliases: - image end_image_url: x-cli-aliases: - end-image prompt: {} required: - prompt additionalProperties: {} - title: Frame type: object properties: feature: type: string enum: - frame-to-video first_frame_url: x-cli-aliases: - first-frame - start-frame last_frame_url: x-cli-aliases: - last-frame - end-frame prompt: {} required: - first_frame_url - prompt additionalProperties: {} - title: Reference type: object properties: feature: type: string enum: - reference-to-video start_image_url: x-cli-aliases: - start-image end_image_url: x-cli-aliases: - end-image image_urls: x-cli-aliases: - image - images maxItems: 4 type: array items: description: >- When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. anyOf: - format: uri type: string - format: binary type: string reference_image_urls: x-cli-aliases: - reference-image - reference-images maxItems: 4 type: array items: description: >- When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. anyOf: - format: uri type: string - format: binary type: string prompt: {} required: - prompt additionalProperties: {} - title: Video Edit type: object properties: feature: type: string enum: - video-to-video video_url: x-cli-aliases: - video keep_audio: {} image_urls: x-cli-aliases: - image - images maxItems: 4 type: array items: description: >- When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. anyOf: - format: uri type: string - format: binary type: string prompt: {} required: - video_url - prompt additionalProperties: {} - title: Video Reference type: object properties: feature: type: string enum: - video-reference-to-video video_url: x-cli-aliases: - video keep_audio: {} aspect_ratio: default: auto type: string enum: - auto - '9:16' - '16:9' - '1:1' image_urls: x-cli-aliases: - image - images maxItems: 4 type: array items: description: >- When using application/json, send a public URL. When using multipart/form-data, send either a public URL or a binary file upload. anyOf: - format: uri type: string - format: binary type: string prompt: {} required: - video_url - prompt additionalProperties: {} kling_ai_o3_videoPrediction: type: object properties: id: description: Generation id. type: string status: $ref: '#/components/schemas/QueueState' input: $ref: '#/components/schemas/kling_ai_o3_videoInputOutput' title: Input xMeta: video_duration: video_url description: Normalized input payload for the generation task. usage: $ref: '#/components/schemas/Usage' code: $ref: '#/components/schemas/__schema1' message: $ref: '#/components/schemas/__schema2' required: - id - status - input - usage additionalProperties: false VideoGenerationErrorResponse: type: object properties: error: description: >- Legacy machine-readable error field. Prefer `code` for new integrations. type: string code: description: >- Video generation error code. `*_FAILED` is the generic fallback; more specific codes (`*_TIMEOUT`, `*_RATE_LIMITED`, `*_PROVIDER_UNAVAILABLE`, `*_UNSUPPORTED_MODEL`, `*_INVALID_INPUT`, `*_INSUFFICIENT_CREDITS`, `*_CONTENT_REJECTED`) are surfaced when applicable. type: string enum: - VIDEO_GENERATION_FAILED - VIDEO_GENERATION_TIMEOUT - VIDEO_GENERATION_RATE_LIMITED - VIDEO_GENERATION_PROVIDER_UNAVAILABLE - VIDEO_GENERATION_UNSUPPORTED_MODEL - VIDEO_GENERATION_INVALID_INPUT - VIDEO_GENERATION_INSUFFICIENT_CREDITS - VIDEO_GENERATION_CONTENT_REJECTED message: description: Human readable error message. Upstream vendor names are redacted. type: string errors: description: Field-level validation errors when available. type: array items: type: object properties: path: type: string message: type: string code: type: string required: - path - message - code additionalProperties: false details: description: Additional structured error details when available. requested: description: Requested credits when the error is insufficient credits. type: number available: description: Available credits when the error is insufficient credits. type: number required: - code - message additionalProperties: false TemplateErrorResponse: type: object properties: error: description: >- Legacy machine-readable error field. Prefer `code` for new integrations. type: string code: description: Template error code. type: string enum: - TEMPLATE_NOT_FOUND - TEMPLATE_MODEL_MISMATCH - TEMPLATE_INVALID_INPUT - TEMPLATE_TRANSFORM_FAILED message: description: Human readable template error message. type: string errors: description: Field-level template validation errors when available. type: array items: type: object properties: path: type: string message: type: string code: type: string required: - path - message - code additionalProperties: false details: description: Additional structured error details when available. required: - code - message additionalProperties: false ErrorResponse: type: object properties: error: description: >- Legacy machine-readable error field. Prefer `code` for new integrations. This may contain an unprefixed compatibility code for older clients. type: string code: description: Machine-readable error code. Use this to branch in client code. type: string message: description: Human readable error message. type: string errors: description: Field-level validation errors when available. type: array items: type: object properties: path: type: string message: type: string code: type: string required: - path - message - code additionalProperties: false details: description: Additional structured error details when available. required: - code - message additionalProperties: false SeedanceVerificationErrorResponse: type: object properties: error: description: >- Legacy machine-readable error field. Prefer `code` for new integrations. type: string code: description: Seedance verification error code. type: string const: SEEDANCE_VERIFICATION_REQUIRED message: description: Human readable verification error message. type: string verification: description: Current Seedance verification state when available. anyOf: - {} - type: 'null' required: - code - message additionalProperties: false kling_ai_o3_videoInput: title: Input oneOf: - title: Text Image To Video allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature type: string const: text-image-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: Start frame image URL for image-to-video. title: Image format: uri type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). title: Start Image format: uri type: string end_image_url: description: End frame image URL for image-to-video / reference-to-video. title: End Image format: uri type: string first_frame_url: description: First frame image URL for frame-to-video mode. title: First Frame format: uri type: string last_frame_url: description: Optional last frame image URL for frame-to-video mode. title: Last Frame format: uri type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). title: Video format: uri xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - title: Text/Image type: object properties: feature: type: string const: text-image-to-video image_url: {} end_image_url: {} prompt: {} required: - prompt additionalProperties: {} - title: Frame To Video allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature type: string const: frame-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: Start frame image URL for image-to-video. title: Image format: uri type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). title: Start Image format: uri type: string end_image_url: description: End frame image URL for image-to-video / reference-to-video. title: End Image format: uri type: string first_frame_url: description: First frame image URL for frame-to-video mode. title: First Frame format: uri type: string last_frame_url: description: Optional last frame image URL for frame-to-video mode. title: Last Frame format: uri type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). title: Video format: uri xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - title: Frame type: object properties: feature: type: string const: frame-to-video first_frame_url: {} last_frame_url: {} prompt: {} required: - first_frame_url - prompt additionalProperties: {} - title: Reference To Video allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature type: string const: reference-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: Start frame image URL for image-to-video. title: Image format: uri type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). title: Start Image format: uri type: string end_image_url: description: End frame image URL for image-to-video / reference-to-video. title: End Image format: uri type: string first_frame_url: description: First frame image URL for frame-to-video mode. title: First Frame format: uri type: string last_frame_url: description: Optional last frame image URL for frame-to-video mode. title: Last Frame format: uri type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). title: Video format: uri xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - title: Reference type: object properties: feature: type: string const: reference-to-video start_image_url: {} end_image_url: {} image_urls: maxItems: 4 type: array items: format: uri type: string reference_image_urls: maxItems: 4 type: array items: format: uri type: string prompt: {} required: - prompt additionalProperties: {} - title: Video To Video allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature type: string const: video-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: Start frame image URL for image-to-video. title: Image format: uri type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). title: Start Image format: uri type: string end_image_url: description: End frame image URL for image-to-video / reference-to-video. title: End Image format: uri type: string first_frame_url: description: First frame image URL for frame-to-video mode. title: First Frame format: uri type: string last_frame_url: description: Optional last frame image URL for frame-to-video mode. title: Last Frame format: uri type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). title: Video format: uri xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - title: Video Edit type: object properties: feature: type: string const: video-to-video video_url: {} keep_audio: {} image_urls: maxItems: 4 type: array items: format: uri type: string prompt: {} required: - video_url - prompt additionalProperties: {} - title: Video Reference To Video allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature type: string const: video-reference-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: Start frame image URL for image-to-video. title: Image format: uri type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). title: Start Image format: uri type: string end_image_url: description: End frame image URL for image-to-video / reference-to-video. title: End Image format: uri type: string first_frame_url: description: First frame image URL for frame-to-video mode. title: First Frame format: uri type: string last_frame_url: description: Optional last frame image URL for frame-to-video mode. title: Last Frame format: uri type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). title: Video format: uri xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - title: Video Reference type: object properties: feature: type: string const: video-reference-to-video video_url: {} keep_audio: {} aspect_ratio: default: auto type: string enum: - auto - '9:16' - '16:9' - '1:1' image_urls: maxItems: 4 type: array items: format: uri type: string prompt: {} required: - video_url - prompt additionalProperties: {} QueueState: description: Queue status type: string enum: - IN_QUEUE - IN_PROGRESS - COMPLETED - FAILED - CANCELED kling_ai_o3_videoInputOutput: $ref: '#/components/schemas/__schema26' title: Input xMeta: video_duration: video_url Usage: description: Credit usage breakdown for the request type: object properties: total: type: integer minimum: -9007199254740991 maximum: 9007199254740991 subscription: type: integer minimum: -9007199254740991 maximum: 9007199254740991 permanent: type: integer minimum: -9007199254740991 maximum: 9007199254740991 required: - total - subscription - permanent additionalProperties: false __schema1: description: >- Machine-readable generation error code. Present when `status` is `FAILED`. type: string __schema2: description: >- Sanitized human-readable failure message. Present when `status` is `FAILED`. type: string __schema26: title: Input oneOf: - title: Text Image To Video allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature type: string const: text-image-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: Start frame image URL for image-to-video. title: Image format: uri type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). title: Start Image format: uri type: string end_image_url: description: End frame image URL for image-to-video / reference-to-video. title: End Image format: uri type: string first_frame_url: description: First frame image URL for frame-to-video mode. title: First Frame format: uri type: string last_frame_url: description: Optional last frame image URL for frame-to-video mode. title: Last Frame format: uri type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). title: Video format: uri xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - title: Text/Image type: object properties: feature: type: string const: text-image-to-video image_url: {} end_image_url: {} prompt: {} required: - prompt additionalProperties: {} - title: Frame To Video allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature type: string const: frame-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: Start frame image URL for image-to-video. title: Image format: uri type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). title: Start Image format: uri type: string end_image_url: description: End frame image URL for image-to-video / reference-to-video. title: End Image format: uri type: string first_frame_url: description: First frame image URL for frame-to-video mode. title: First Frame format: uri type: string last_frame_url: description: Optional last frame image URL for frame-to-video mode. title: Last Frame format: uri type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). title: Video format: uri xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - title: Frame type: object properties: feature: type: string const: frame-to-video first_frame_url: {} last_frame_url: {} prompt: {} required: - first_frame_url - prompt additionalProperties: {} - title: Reference To Video allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature type: string const: reference-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: Start frame image URL for image-to-video. title: Image format: uri type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). title: Start Image format: uri type: string end_image_url: description: End frame image URL for image-to-video / reference-to-video. title: End Image format: uri type: string first_frame_url: description: First frame image URL for frame-to-video mode. title: First Frame format: uri type: string last_frame_url: description: Optional last frame image URL for frame-to-video mode. title: Last Frame format: uri type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). title: Video format: uri xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - title: Reference type: object properties: feature: type: string const: reference-to-video start_image_url: {} end_image_url: {} image_urls: maxItems: 4 type: array items: format: uri type: string reference_image_urls: maxItems: 4 type: array items: format: uri type: string prompt: {} required: - prompt additionalProperties: {} - title: Video To Video allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature type: string const: video-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: Start frame image URL for image-to-video. title: Image format: uri type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). title: Start Image format: uri type: string end_image_url: description: End frame image URL for image-to-video / reference-to-video. title: End Image format: uri type: string first_frame_url: description: First frame image URL for frame-to-video mode. title: First Frame format: uri type: string last_frame_url: description: Optional last frame image URL for frame-to-video mode. title: Last Frame format: uri type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). title: Video format: uri xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - title: Video Edit type: object properties: feature: type: string const: video-to-video video_url: {} keep_audio: {} image_urls: maxItems: 4 type: array items: format: uri type: string prompt: {} required: - video_url - prompt additionalProperties: {} - title: Video Reference To Video allOf: - title: Input xMeta: video_duration: video_url type: object properties: feature: description: >- Workflow type: text/image-to-video, frame-to-video, reference-to-video, video-to-video (edit), or video-reference-to-video. title: Feature type: string const: video-reference-to-video prompt: description: Text prompt for video generation title: Prompt type: string duration: description: Video duration in seconds title: Duration order: 3 default: 5 type: integer minimum: 3 maximum: 15 generate_audio: description: Whether to generate audio for the video title: Generate Audio default: true type: boolean keep_audio: description: >- Preserves original audio from the reference video (video-to-video modes). title: Keep Audio default: true type: boolean quality: description: generation quality title: quality order: 5 default: pro type: string enum: - standard - pro aspect_ratio: description: >- Aspect ratio of the video. Portrait is 720x1280, landscape is 1280x720 title: aspect_ratio order: 4 default: '16:9' type: string enum: - '9:16' - '16:9' - '1:1' image_url: description: Start frame image URL for image-to-video. title: Image format: uri type: string start_image_url: description: >- Start frame image URL (alias for image_url in reference-to-video mode). title: Start Image format: uri type: string end_image_url: description: End frame image URL for image-to-video / reference-to-video. title: End Image format: uri type: string first_frame_url: description: First frame image URL for frame-to-video mode. title: First Frame format: uri type: string last_frame_url: description: Optional last frame image URL for frame-to-video mode. title: Last Frame format: uri type: string image_urls: description: >- Reference images for style/appearance; cite in prompt as @Image1, @Image2. Max 4 total (combined with elements). title: Reference Images order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' reference_image_urls: description: Compatibility alias for image_urls. title: Reference Images (alias) order: 3 anyOf: - maxItems: 4 type: array items: format: uri type: string - type: 'null' video_url: description: >- Reference video URL for video-to-video modes (mp4/mov, 3-10s, 720-2160px, max 200MB). title: Video format: uri xMeta: allowedVideoExtensions: - mp4 - mov combinedDurationRange: min: 3 max: 10 maxSizeBytesPerFile: 209715200 type: string negative_prompt: description: Description of what to exclude from the generated video title: Negative Prompt anyOf: - type: string - type: 'null' required: - prompt additionalProperties: {} - title: Video Reference type: object properties: feature: type: string const: video-reference-to-video video_url: {} keep_audio: {} aspect_ratio: default: auto type: string enum: - auto - '9:16' - '16:9' - '1:1' image_urls: maxItems: 4 type: array items: format: uri type: string prompt: {} required: - video_url - prompt additionalProperties: {} securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: API Key for API endpoints ````