> ## Documentation Index > Fetch the complete documentation index at: https://hedra.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Generate Asset ## OpenAPI ````yaml openapi.json post /generations openapi: 3.1.0 info: title: Hedra Web API version: 0.1.0 servers: - url: https://api.hedra.com/web-app/public description: Hedra Public API security: [] paths: /generations: post: tags: - Public summary: Generate Asset operationId: generate_asset_public_generations_post requestBody: required: true content: application/json: schema: oneOf: - $ref: '#/components/schemas/GenerateVideoRequest-Input' - $ref: '#/components/schemas/GenerateTextToSpeechRequest' - $ref: '#/components/schemas/GenerateTextToSoundRequest' - $ref: '#/components/schemas/GenerateImageRequest' - $ref: '#/components/schemas/GenerateImageUpscaleRequest' - $ref: '#/components/schemas/GenerateVideoUpscaleRequest' - $ref: '#/components/schemas/GenerateIsolatedAudioRequest' - $ref: '#/components/schemas/GenerateSpeechToSpeechRequest' - $ref: '#/components/schemas/GenerateVoiceCloneRequest' - $ref: '#/components/schemas/GenerateAudioFromVideoRequest' - $ref: '#/components/schemas/GenerateVideoWithAudioRequest' - $ref: '#/components/schemas/GenerateVideoToVideoRequest' - $ref: '#/components/schemas/GenerateMotionControlRequest-Input' discriminator: propertyName: type mapping: video: $ref: '#/components/schemas/GenerateVideoRequest-Input' text_to_speech: $ref: '#/components/schemas/GenerateTextToSpeechRequest' text_to_sound: $ref: '#/components/schemas/GenerateTextToSoundRequest' image: $ref: '#/components/schemas/GenerateImageRequest' image_to_image: $ref: '#/components/schemas/GenerateImageRequest' image_upscale: $ref: '#/components/schemas/GenerateImageUpscaleRequest' video_upscale: $ref: '#/components/schemas/GenerateVideoUpscaleRequest' audio_isolation: $ref: '#/components/schemas/GenerateIsolatedAudioRequest' speech_to_speech: $ref: '#/components/schemas/GenerateSpeechToSpeechRequest' voice_clone: $ref: '#/components/schemas/GenerateVoiceCloneRequest' audio_from_video: $ref: '#/components/schemas/GenerateAudioFromVideoRequest' video_with_audio: $ref: '#/components/schemas/GenerateVideoWithAudioRequest' video_to_video: $ref: '#/components/schemas/GenerateVideoToVideoRequest' motion_control: $ref: '#/components/schemas/GenerateMotionControlRequest-Input' title: Generate Request responses: '200': description: Successful Response content: application/json: schema: oneOf: - $ref: '#/components/schemas/GenerateVideoResponse' - $ref: '#/components/schemas/GenerateTextToSpeechResponse' - $ref: '#/components/schemas/GenerateTextToSoundResponse' - $ref: '#/components/schemas/GenerateImageResponse' - $ref: '#/components/schemas/GenerateImageUpscaleResponse' - $ref: '#/components/schemas/GenerateVideoUpscaleResponse' - $ref: '#/components/schemas/GenerateIsolatedAudioResponse' - $ref: '#/components/schemas/GenerateSpeechToSpeechResponse' - $ref: '#/components/schemas/GenerateVoiceCloneResponse' - $ref: '#/components/schemas/GenerateAudioFromVideoResponse' - $ref: '#/components/schemas/GenerateVideoWithAudioResponse' - $ref: '#/components/schemas/GenerateVideoToVideoResponse' - $ref: '#/components/schemas/GenerateMotionControlResponse' discriminator: propertyName: type mapping: video: $ref: '#/components/schemas/GenerateVideoResponse' text_to_speech: $ref: '#/components/schemas/GenerateTextToSpeechResponse' text_to_sound: $ref: '#/components/schemas/GenerateTextToSoundResponse' image: $ref: '#/components/schemas/GenerateImageResponse' image_to_image: $ref: '#/components/schemas/GenerateImageResponse' image_upscale: $ref: '#/components/schemas/GenerateImageUpscaleResponse' video_upscale: $ref: '#/components/schemas/GenerateVideoUpscaleResponse' audio_isolation: $ref: '#/components/schemas/GenerateIsolatedAudioResponse' speech_to_speech: $ref: '#/components/schemas/GenerateSpeechToSpeechResponse' voice_clone: $ref: '#/components/schemas/GenerateVoiceCloneResponse' audio_from_video: $ref: '#/components/schemas/GenerateAudioFromVideoResponse' video_with_audio: $ref: '#/components/schemas/GenerateVideoWithAudioResponse' video_to_video: $ref: '#/components/schemas/GenerateVideoToVideoResponse' motion_control: $ref: '#/components/schemas/GenerateMotionControlResponse' title: Response Generate Asset Public Generations Post '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - APIKeyHeader: [] components: schemas: GenerateVideoRequest-Input: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: video title: Type default: video ai_model_id: type: string format: uuid title: Ai Model Id description: ID of the model to use for the generation. default: d1dd37a3-e39a-4854-a298-6510289f9cf2 start_keyframe_id: anyOf: - type: string format: uuid - type: 'null' title: Start Keyframe Id description: >- The id of the Image asset to use as the start keyframe. This will be ignored if reference_image_ids is provided. start_keyframe_url: anyOf: - type: string maxLength: 2083 minLength: 1 format: uri - type: 'null' title: Start Keyframe Url description: The URL of the image to use as the start keyframe. end_keyframe_id: anyOf: - type: string format: uuid - type: 'null' title: End Keyframe Id description: >- The id of the Image asset to use as the end keyframe. This will be ignored if reference_image_ids is provided. end_keyframe_url: anyOf: - type: string maxLength: 2083 minLength: 1 format: uri - type: 'null' title: End Keyframe Url description: The URL of the image to use as the end keyframe. audio_id: anyOf: - type: string format: uuid - type: 'null' title: Audio Id description: The id of the Audio asset to use. audio_generation: anyOf: - $ref: '#/components/schemas/GenerateTextToSpeechRequest' - type: 'null' description: >- Optional TTS parameters for server-side audio generation. If provided (and audio_id is not), audio will be generated from these params before video generation. audio_start_ms: anyOf: - type: integer - type: 'null' title: Audio Start Ms description: >- Audio start offset in milliseconds. Negative values prepend silence (e.g., -1000 adds 1s silence before audio). Positive values crop from the beginning of the source audio (e.g., 2000 skips the first 2s). Use with generated_video_inputs.duration_ms to control total output length. reference_image_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Reference Image Ids description: >- The id(s) of the image(s) to reference in the generation. Only used for multi-image video generation and will supersede start_keyframe_id. video_id: anyOf: - type: string format: uuid - type: 'null' title: Video Id description: >- The id of the Video asset to use as motion input for V2V (motion control) models. generated_video_inputs: $ref: '#/components/schemas/GeneratedVideoInputs' description: Inputs for generating the video. batch_size: type: integer maximum: 8 minimum: 1 title: Batch Size description: >- Number of video variations to generate (1-8). When > 1, batch_results will contain all generation results. default: 1 type: object required: - generated_video_inputs title: GenerateVideoRequest GenerateTextToSpeechRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: text_to_speech title: Type default: text_to_speech voice_id: type: string format: uuid title: Voice Id description: The id of the Voice to use. model_id: anyOf: - type: string format: uuid - type: 'null' title: Model Id description: The id of the model to use. text: type: string title: Text description: The text to convert to speech. stability: type: number maximum: 1 minimum: 0 title: Stability description: >- Stability should be between 0-1, where 0 is the most stable and 1 is the most unstable. This varies the consistency between your outputs. default: 1 speed: type: number maximum: 1.2 minimum: 0.7 title: Speed description: >- Speed should be between 0.7 and 1.2, where 0.7 is the slowest and 1.2 is the fastest. This varies the speed of the generated speech. default: 1 language: $ref: '#/components/schemas/SupportedLanguage' description: >- Language for TTS. See SupportedLanguage enum for valid values. Defaults to 'auto'. default: auto type: object required: - voice_id - text title: GenerateTextToSpeechRequest GenerateTextToSoundRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: text_to_sound title: Type default: text_to_sound ai_model_id: type: string format: uuid title: Ai Model Id description: The id of the model to use for sound effect generation. text: type: string title: Text description: The text description of the sound effect to generate. duration_seconds: anyOf: - type: number maximum: 30 minimum: 0.5 - type: 'null' title: Duration Seconds description: >- The duration of the sound effect in seconds (0.5-30). If not specified, duration is automatically determined from the prompt. prompt_influence: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Prompt Influence description: >- Controls how strictly the model follows the prompt (0-1). Higher values mean more literal interpretation. Defaults to 0.3. loop: anyOf: - type: boolean - type: 'null' title: Loop description: >- Whether to create a sound effect that loops smoothly. Only available for the eleven_text_to_sound_v2 model. output_format: anyOf: - type: string - type: 'null' title: Output Format description: >- Output format of the generated audio. Formatted as codec_sample_rate_bitrate (e.g., mp3_22050_32, mp3_44100_128, pcm_44100). If not specified, defaults to mp3_44100_128. default: mp3_44100_128 type: object required: - ai_model_id - text title: GenerateTextToSoundRequest GenerateImageRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string enum: - image - image_to_image title: Type default: image text_prompt: type: string title: Text Prompt description: The text prompt for image generation or image editing. aspect_ratio: anyOf: - type: string - type: 'null' title: Aspect Ratio description: The aspect ratio to use. resolution: anyOf: - type: string - type: 'null' title: Resolution description: >- The resolution to use formatted like '540p', '1080p', '1440p (2K QHD)', etc. start_keyframe_id: anyOf: - type: string format: uuid - type: 'null' title: Start Keyframe Id description: >- The id of the Image asset to use as the start keyframe. This will be ignored if reference_image_ids is provided. ai_model_id: type: string format: uuid title: Ai Model Id description: The model to use. reference_image_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Reference Image Ids description: >- The id(s) of the image(s) to reference in the generation. This is only used for image-to-image generation and will supersede start_keyframe_id. batch_size: type: integer maximum: 8 minimum: 1 title: Batch Size description: >- Number of image variations to generate (1-8). When > 1, batch_results will contain all generation results. default: 1 enhance_prompt: type: boolean title: Enhance Prompt description: If true, automatically enhance the prompt before generation. default: false type: object required: - text_prompt - ai_model_id title: GenerateImageRequest GenerateImageUpscaleRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: image_upscale title: Type default: image_upscale ai_model_id: type: string format: uuid title: Ai Model Id description: The model to use for upscaling. image_id: type: string format: uuid title: Image Id description: The id of the Image asset to use as the basis for upscaling. upscale_factor: anyOf: - type: number - type: 'null' title: Upscale Factor description: Optional upscale factor to pass to the model (e.g. 2.0 for 2x). type: object required: - ai_model_id - image_id title: GenerateImageUpscaleRequest GenerateVideoUpscaleRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: video_upscale title: Type default: video_upscale ai_model_id: type: string format: uuid title: Ai Model Id description: The model to use for upscaling. video_id: type: string format: uuid title: Video Id description: The id of the Video asset to upscale. upscale_factor: type: number maximum: 4 exclusiveMinimum: 0 title: Upscale Factor description: >- Scale factor for upscaling (e.g., 1.5 for 1.5x, 2.0 for 2x). Default: 1.5 default: 1.5 type: object required: - ai_model_id - video_id title: GenerateVideoUpscaleRequest GenerateIsolatedAudioRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: audio_isolation title: Type default: audio_isolation audio_id: type: string format: uuid title: Audio Id description: The id of the audio asset requiring sound isolation. ai_model_id: type: string format: uuid title: Ai Model Id description: The id of the model to use for audio isolation. type: object required: - audio_id - ai_model_id title: GenerateIsolatedAudioRequest GenerateSpeechToSpeechRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: speech_to_speech title: Type default: speech_to_speech audio_id: type: string format: uuid title: Audio Id description: The id of the audio asset requiring sound isolation. ai_model_id: type: string format: uuid title: Ai Model Id description: The id of the model to use for audio isolation. voice_id: type: string format: uuid title: Voice Id description: The id of the Voice to use. type: object required: - audio_id - ai_model_id - voice_id title: GenerateSpeechToSpeechRequest GenerateVoiceCloneRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: voice_clone title: Type default: voice_clone audio_id: type: string format: uuid title: Audio Id description: The id of the Audio asset to use as the basis for the clone. name: type: string title: Name description: >- The name of the new voice. Required by ElevenLabs to create a new voice. type: object required: - audio_id - name title: GenerateVoiceCloneRequest GenerateAudioFromVideoRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: audio_from_video title: Type default: audio_from_video audio_generation_model_id: type: string format: uuid title: Audio Generation Model Id description: >- ID of the model to use for video-to-audio generation (Mirelo Studio). video_id: type: string format: uuid title: Video Id description: The id of the video asset to generate audio from. prompt: anyOf: - type: string - type: 'null' title: Prompt description: Optional prompt to guide the audio generation. type: object required: - audio_generation_model_id - video_id title: GenerateAudioFromVideoRequest description: >- Audio generation request that extracts sound effects from video using Mirelo Studio. GenerateVideoWithAudioRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: video_with_audio title: Type default: video_with_audio video_generation_model_id: type: string format: uuid title: Video Generation Model Id description: >- ID of the model to use for video-to-video with audio generation (Mirelo Studio). video_id: type: string format: uuid title: Video Id description: The id of the video asset to add sound effects to. prompt: anyOf: - type: string - type: 'null' title: Prompt description: Optional prompt to guide the audio generation for the video. type: object required: - video_generation_model_id - video_id title: GenerateVideoWithAudioRequest description: >- Video generation request that adds synchronized sound effects to video using Mirelo Studio. GenerateVideoToVideoRequest: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: video_to_video title: Type default: video_to_video ai_model_id: type: string format: uuid title: Ai Model Id description: The id of the model to use for video-to-video generation. video_id: type: string format: uuid title: Video Id description: The id of the video asset to transform. prompt: type: string title: Prompt description: >- Natural language transformation instructions. Use @Element1, @Image1 syntax to reference elements and images. reference_image_asset_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Reference Image Asset Ids description: >- Optional ids of reference image assets for style transfer. Reference as @Image1, @Image2, etc. in prompt. elements: anyOf: - items: $ref: '#/components/schemas/KlingO1EditElement' type: array - type: 'null' title: Elements description: >- Optional elements for character tracking. Reference as @Element1, @Element2, etc. in prompt. keep_audio: type: boolean title: Keep Audio description: Whether to preserve the original audio from the input video. default: false type: object required: - ai_model_id - video_id - prompt title: GenerateVideoToVideoRequest description: |- Video-to-video edit request for Kling O1 Edit model. Transforms videos using natural language while preserving motion. GenerateMotionControlRequest-Input: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: motion_control title: Type default: motion_control ai_model_id: type: string format: uuid title: Ai Model Id description: The id of the Motion Control model to use. video_id: type: string format: uuid title: Video Id description: The id of the video asset to use as motion reference. start_keyframe_id: type: string format: uuid title: Start Keyframe Id description: >- The id of the character image asset to animate with the motion from the video. generated_video_inputs: $ref: '#/components/schemas/GeneratedVideoInputs' description: >- Video generation parameters including text_prompt and character_orientation. type: object required: - ai_model_id - video_id - start_keyframe_id - generated_video_inputs title: GenerateMotionControlRequest description: >- Motion Control request for transferring motion from a reference video to a character image. Processed through V2V infrastructure internally. GenerateVideoResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: video title: Type default: video ai_model_id: type: string format: uuid title: Ai Model Id description: ID of the model to use for the generation. default: d1dd37a3-e39a-4854-a298-6510289f9cf2 start_keyframe_id: anyOf: - type: string format: uuid - type: 'null' title: Start Keyframe Id description: >- The id of the Image asset to use as the start keyframe. This will be ignored if reference_image_ids is provided. start_keyframe_url: anyOf: - type: string maxLength: 2083 minLength: 1 format: uri - type: 'null' title: Start Keyframe Url description: The URL of the image to use as the start keyframe. end_keyframe_id: anyOf: - type: string format: uuid - type: 'null' title: End Keyframe Id description: >- The id of the Image asset to use as the end keyframe. This will be ignored if reference_image_ids is provided. end_keyframe_url: anyOf: - type: string maxLength: 2083 minLength: 1 format: uri - type: 'null' title: End Keyframe Url description: The URL of the image to use as the end keyframe. audio_id: anyOf: - type: string format: uuid - type: 'null' title: Audio Id description: The id of the Audio asset to use. audio_generation: anyOf: - $ref: '#/components/schemas/GenerateTextToSpeechRequest' - type: 'null' description: >- Optional TTS parameters for server-side audio generation. If provided (and audio_id is not), audio will be generated from these params before video generation. audio_start_ms: anyOf: - type: integer - type: 'null' title: Audio Start Ms description: >- Audio start offset in milliseconds. Negative values prepend silence (e.g., -1000 adds 1s silence before audio). Positive values crop from the beginning of the source audio (e.g., 2000 skips the first 2s). Use with generated_video_inputs.duration_ms to control total output length. reference_image_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Reference Image Ids description: >- The id(s) of the image(s) to reference in the generation. Only used for multi-image video generation and will supersede start_keyframe_id. video_id: anyOf: - type: string format: uuid - type: 'null' title: Video Id description: >- The id of the Video asset to use as motion input for V2V (motion control) models. generated_video_inputs: $ref: '#/components/schemas/GeneratedVideoInputs' description: Inputs for generating the video. batch_size: type: integer maximum: 8 minimum: 1 title: Batch Size description: >- Number of video variations to generate (1-8). When > 1, batch_results will contain all generation results. default: 1 id: type: string format: uuid title: Id description: The id of the generation created. asset_id: type: string format: uuid title: Asset Id description: The id of the video asset resulting from the generation. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. batch_generation_id: anyOf: - type: string - type: 'null' title: Batch Generation Id description: Unique identifier linking all generations in a batch. batch_results: items: $ref: '#/components/schemas/BatchVideoResultItem' type: array title: Batch Results description: >- All generation results in the batch. Always populated (even for batch_size=1). The main response fields (id, asset_id, etc.) reflect the first successful generation. type: object required: - generated_video_inputs - id - asset_id - created_at - status - progress title: GenerateVideoResponse GenerateTextToSpeechResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: text_to_speech title: Type default: text_to_speech voice_id: type: string format: uuid title: Voice Id description: The id of the Voice to use. model_id: anyOf: - type: string format: uuid - type: 'null' title: Model Id description: The id of the model to use. text: type: string title: Text description: The text to convert to speech. stability: type: number maximum: 1 minimum: 0 title: Stability description: >- Stability should be between 0-1, where 0 is the most stable and 1 is the most unstable. This varies the consistency between your outputs. default: 1 speed: type: number maximum: 1.2 minimum: 0.7 title: Speed description: >- Speed should be between 0.7 and 1.2, where 0.7 is the slowest and 1.2 is the fastest. This varies the speed of the generated speech. default: 1 language: $ref: '#/components/schemas/SupportedLanguage' description: >- Language for TTS. See SupportedLanguage enum for valid values. Defaults to 'auto'. default: auto asset_id: type: string format: uuid title: Asset Id description: The id of the audio asset resulting from the generation. id: type: string format: uuid title: Id description: The id of the generation created. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - voice_id - text - asset_id - id - created_at - status - progress title: GenerateTextToSpeechResponse GenerateTextToSoundResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: text_to_sound title: Type default: text_to_sound ai_model_id: type: string format: uuid title: Ai Model Id description: The id of the model to use for sound effect generation. text: type: string title: Text description: The text description of the sound effect to generate. duration_seconds: anyOf: - type: number maximum: 30 minimum: 0.5 - type: 'null' title: Duration Seconds description: >- The duration of the sound effect in seconds (0.5-30). If not specified, duration is automatically determined from the prompt. prompt_influence: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Prompt Influence description: >- Controls how strictly the model follows the prompt (0-1). Higher values mean more literal interpretation. Defaults to 0.3. loop: anyOf: - type: boolean - type: 'null' title: Loop description: >- Whether to create a sound effect that loops smoothly. Only available for the eleven_text_to_sound_v2 model. output_format: anyOf: - type: string - type: 'null' title: Output Format description: >- Output format of the generated audio. Formatted as codec_sample_rate_bitrate (e.g., mp3_22050_32, mp3_44100_128, pcm_44100). If not specified, defaults to mp3_44100_128. default: mp3_44100_128 id: type: string format: uuid title: Id description: The id of the generation created. asset_id: type: string format: uuid title: Asset Id description: The id of the audio asset resulting from the generation. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - ai_model_id - text - id - asset_id - created_at - status - progress title: GenerateTextToSoundResponse GenerateImageResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string enum: - image - image_to_image title: Type default: image text_prompt: type: string title: Text Prompt description: The text prompt for image generation or image editing. aspect_ratio: anyOf: - type: string - type: 'null' title: Aspect Ratio description: The aspect ratio to use. resolution: anyOf: - type: string - type: 'null' title: Resolution description: >- The resolution to use formatted like '540p', '1080p', '1440p (2K QHD)', etc. start_keyframe_id: anyOf: - type: string format: uuid - type: 'null' title: Start Keyframe Id description: >- The id of the Image asset to use as the start keyframe. This will be ignored if reference_image_ids is provided. ai_model_id: type: string format: uuid title: Ai Model Id description: The model to use. reference_image_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Reference Image Ids description: >- The id(s) of the image(s) to reference in the generation. This is only used for image-to-image generation and will supersede start_keyframe_id. batch_size: type: integer maximum: 8 minimum: 1 title: Batch Size description: >- Number of image variations to generate (1-8). When > 1, batch_results will contain all generation results. default: 1 enhance_prompt: type: boolean title: Enhance Prompt description: If true, automatically enhance the prompt before generation. default: false asset_id: type: string format: uuid title: Asset Id description: The id of the resulting image asset. id: type: string format: uuid title: Id description: The id of the generation. Can be used to check status. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. batch_generation_id: anyOf: - type: string - type: 'null' title: Batch Generation Id description: Unique identifier linking all generations in a batch. batch_results: items: $ref: '#/components/schemas/BatchImageResultItem' type: array title: Batch Results description: >- All generation results in the batch. Always populated (even for batch_size=1). The main response fields (id, asset_id, etc.) reflect the first successful generation. type: object required: - text_prompt - ai_model_id - asset_id - id - created_at - status - progress title: GenerateImageResponse GenerateImageUpscaleResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: image_upscale title: Type default: image_upscale ai_model_id: type: string format: uuid title: Ai Model Id description: The model to use for upscaling. image_id: type: string format: uuid title: Image Id description: The id of the Image asset to use as the basis for upscaling. upscale_factor: anyOf: - type: number - type: 'null' title: Upscale Factor description: Optional upscale factor to pass to the model (e.g. 2.0 for 2x). asset_id: type: string format: uuid title: Asset Id description: The id of the resulting image asset. id: type: string format: uuid title: Id description: The id of the generation. Can be used to check status. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - ai_model_id - image_id - asset_id - id - created_at - status - progress title: GenerateImageUpscaleResponse GenerateVideoUpscaleResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: video_upscale title: Type default: video_upscale ai_model_id: type: string format: uuid title: Ai Model Id description: The model to use for upscaling. video_id: type: string format: uuid title: Video Id description: The id of the Video asset to upscale. upscale_factor: type: number maximum: 4 exclusiveMinimum: 0 title: Upscale Factor description: >- Scale factor for upscaling (e.g., 1.5 for 1.5x, 2.0 for 2x). Default: 1.5 default: 1.5 asset_id: type: string format: uuid title: Asset Id description: The id of the resulting upscaled video asset. id: type: string format: uuid title: Id description: The id of the generation. Can be used to check status. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - ai_model_id - video_id - asset_id - id - created_at - status - progress title: GenerateVideoUpscaleResponse GenerateIsolatedAudioResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: audio_isolation title: Type default: audio_isolation audio_id: type: string format: uuid title: Audio Id description: The id of the audio asset requiring sound isolation. ai_model_id: type: string format: uuid title: Ai Model Id description: The id of the model to use for audio isolation. id: type: string format: uuid title: Id description: The id of the generation created. asset_id: type: string format: uuid title: Asset Id description: The id of the isolated audio asset resulting from the generation. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - audio_id - ai_model_id - id - asset_id - created_at - status - progress title: GenerateIsolatedAudioResponse GenerateSpeechToSpeechResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: speech_to_speech title: Type default: speech_to_speech audio_id: type: string format: uuid title: Audio Id description: The id of the audio asset requiring sound isolation. ai_model_id: type: string format: uuid title: Ai Model Id description: The id of the model to use for audio isolation. voice_id: type: string format: uuid title: Voice Id description: The id of the Voice to use. id: type: string format: uuid title: Id description: The id of the generation created. asset_id: type: string format: uuid title: Asset Id description: The id of the isolated audio asset resulting from the generation. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - audio_id - ai_model_id - voice_id - id - asset_id - created_at - status - progress title: GenerateSpeechToSpeechResponse GenerateVoiceCloneResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: voice_clone title: Type default: voice_clone audio_id: type: string format: uuid title: Audio Id description: The id of the Audio asset to use as the basis for the clone. name: type: string title: Name description: >- The name of the new voice. Required by ElevenLabs to create a new voice. id: type: string format: uuid title: Id description: The id of the generation. Can be used to check status. asset_id: type: string format: uuid title: Asset Id description: The id of the resulting Voice asset. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - audio_id - name - id - asset_id - created_at - status - progress title: GenerateVoiceCloneResponse GenerateAudioFromVideoResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: audio_from_video title: Type default: audio_from_video audio_generation_model_id: type: string format: uuid title: Audio Generation Model Id description: >- ID of the model to use for video-to-audio generation (Mirelo Studio). video_id: type: string format: uuid title: Video Id description: The id of the video asset to generate audio from. prompt: anyOf: - type: string - type: 'null' title: Prompt description: Optional prompt to guide the audio generation. id: type: string format: uuid title: Id description: The id of the generation created. asset_id: anyOf: - type: string format: uuid - type: 'null' title: Asset Id description: >- The id of the audio asset resulting from the generation. Only present when generation is complete. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - audio_generation_model_id - video_id - id - created_at - status - progress title: GenerateAudioFromVideoResponse GenerateVideoWithAudioResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: video_with_audio title: Type default: video_with_audio video_generation_model_id: type: string format: uuid title: Video Generation Model Id description: >- ID of the model to use for video-to-video with audio generation (Mirelo Studio). video_id: type: string format: uuid title: Video Id description: The id of the video asset to add sound effects to. prompt: anyOf: - type: string - type: 'null' title: Prompt description: Optional prompt to guide the audio generation for the video. id: type: string format: uuid title: Id description: The id of the generation created. asset_id: anyOf: - type: string format: uuid - type: 'null' title: Asset Id description: >- The id of the video asset with audio resulting from the generation. Only present when generation is complete. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - video_generation_model_id - video_id - id - created_at - status - progress title: GenerateVideoWithAudioResponse GenerateVideoToVideoResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: video_to_video title: Type default: video_to_video ai_model_id: type: string format: uuid title: Ai Model Id description: The id of the model to use for video-to-video generation. video_id: type: string format: uuid title: Video Id description: The id of the video asset to transform. prompt: type: string title: Prompt description: >- Natural language transformation instructions. Use @Element1, @Image1 syntax to reference elements and images. reference_image_asset_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Reference Image Asset Ids description: >- Optional ids of reference image assets for style transfer. Reference as @Image1, @Image2, etc. in prompt. elements: anyOf: - items: $ref: '#/components/schemas/KlingO1EditElement' type: array - type: 'null' title: Elements description: >- Optional elements for character tracking. Reference as @Element1, @Element2, etc. in prompt. keep_audio: type: boolean title: Keep Audio description: Whether to preserve the original audio from the input video. default: false id: type: string format: uuid title: Id description: The id of the generation. Can be used to check status. asset_id: type: string format: uuid title: Asset Id description: The id of the output video asset. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation. progress: type: number title: Progress description: Current progress to completion. Between 0-1. eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - ai_model_id - video_id - prompt - id - asset_id - created_at - status - progress title: GenerateVideoToVideoResponse GenerateMotionControlResponse: properties: workspace_id: anyOf: - type: string - type: 'null' title: Workspace Id agent_thread_id: anyOf: - type: string format: uuid - type: 'null' title: Agent Thread Id description: Optional agent thread ID to associate this generation with. generation_id: anyOf: - type: string format: uuid - type: 'null' title: Generation Id description: >- Optional pre-reserved generation ID. If provided, this ID will be used instead of generating a new one. For batch operations (batch_size > 1), use generation_ids instead. generation_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Generation Ids description: >- Optional list of pre-reserved generation IDs for batch operations. Length must match batch_size. Mutually exclusive with generation_id. type: type: string const: motion_control title: Type default: motion_control ai_model_id: type: string format: uuid title: Ai Model Id description: The id of the Motion Control model to use. video_id: type: string format: uuid title: Video Id description: The id of the video asset to use as motion reference. start_keyframe_id: type: string format: uuid title: Start Keyframe Id description: >- The id of the character image asset to animate with the motion from the video. generated_video_inputs: $ref: '#/components/schemas/GeneratedVideoInputs' description: >- Video generation parameters including text_prompt and character_orientation. id: type: string format: uuid title: Id description: The id of the generation. Can be used to check status. asset_id: type: string format: uuid title: Asset Id description: The id of the output video asset. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation. progress: type: number title: Progress description: Current progress to completion. Between 0-1. eta_sec: anyOf: - type: integer - type: 'null' title: Eta Sec description: >- Estimated time until completion in seconds. May be None if no historical data available. type: object required: - ai_model_id - video_id - start_keyframe_id - generated_video_inputs - id - asset_id - created_at - status - progress title: GenerateMotionControlResponse description: Response for Motion Control generations. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError GeneratedVideoInputs: properties: text_prompt: type: string title: Text Prompt description: Prompt for video generation. ai_model_id: anyOf: - type: string format: uuid - type: 'null' title: Ai Model Id description: The id of the model used for generation. resolution: anyOf: - type: string - type: 'null' title: Resolution description: Resolution for the video. aspect_ratio: anyOf: - type: string - type: 'null' title: Aspect Ratio description: Aspect ratio for the video. duration_ms: anyOf: - type: integer - type: 'null' title: Duration Ms description: Duration of the video in milliseconds. bounding_box_target: anyOf: - $ref: '#/components/schemas/NormalizedPoint' - type: 'null' description: >- Normalized coordinates for primary speaker position (Character3 only) character_orientation: anyOf: - type: string enum: - video - image - type: 'null' title: Character Orientation description: >- For motion control models: 'video' matches reference video orientation (better for complex motions, max 30s), 'image' preserves character image orientation (better for camera movements, max 10s). enhance_prompt: type: boolean title: Enhance Prompt description: If true, automatically enhance the prompt before generation. default: false type: object required: - text_prompt title: GeneratedVideoInputs SupportedLanguage: type: string enum: - Chinese - Chinese,Yue - English - Arabic - Russian - Spanish - French - Portuguese - German - Turkish - Dutch - Ukrainian - Vietnamese - Indonesian - Japanese - Italian - Korean - Thai - Polish - Romanian - Greek - Czech - Finnish - Hindi - Bulgarian - Danish - Hebrew - Malay - Persian - Slovak - Swedish - Croatian - Filipino - Hungarian - Norwegian - Slovenian - Catalan - Nynorsk - Tamil - Afrikaans - auto title: SupportedLanguage KlingO1EditElement: properties: frontal_image_asset_id: type: string format: uuid title: Frontal Image Asset Id description: ID of the frontal image asset for this element. reference_image_asset_ids: anyOf: - items: type: string format: uuid type: array - type: 'null' title: Reference Image Asset Ids description: >- Optional IDs of additional reference image assets (different angles). type: object required: - frontal_image_asset_id title: KlingO1EditElement description: |- Element for character tracking in Kling O1 Edit. Reference as @Element1, @Element2, etc. in prompt. GenerationStatus: type: string enum: - complete - error - processing - queued - finalizing title: GenerationStatus BatchVideoResultItem: properties: id: anyOf: - type: string format: uuid - type: 'null' title: Id description: The id of the generation created. None if failed. asset_id: anyOf: - type: string format: uuid - type: 'null' title: Asset Id description: >- The id of the video asset resulting from the generation. None if failed. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 error: anyOf: - type: string - type: 'null' title: Error description: Error message if this item failed. type: object required: - created_at - status - progress title: BatchVideoResultItem description: Individual result item in a batch video generation. BatchImageResultItem: properties: id: anyOf: - type: string format: uuid - type: 'null' title: Id description: The id of the generation created. None if failed. asset_id: anyOf: - type: string format: uuid - type: 'null' title: Asset Id description: >- The id of the image asset resulting from the generation. None if failed. created_at: type: string title: Created At description: Date the generation was submitted. status: $ref: '#/components/schemas/GenerationStatus' description: Status of the generation progress: type: number title: Progress description: Current progress to completion. Between 0-1 error: anyOf: - type: string - type: 'null' title: Error description: Error message if this item failed. type: object required: - created_at - status - progress title: BatchImageResultItem description: Individual result item in a batch image generation. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError NormalizedPoint: prefixItems: - type: number maximum: 1 minimum: 0 title: X description: Normalized x coordinate. - type: number maximum: 1 minimum: 0 title: 'Y' description: Normalized y coordinate. type: array maxItems: 2 minItems: 2 securitySchemes: APIKeyHeader: type: apiKey in: header name: X-API-Key ````