The Kling 3.0 series models API is now fully available Learn More Get Started Overview Quick Start Changelog API Reference General Info Rate Limits Callback Schema Video Generation Models Video Omni Text to Video Image to Video Reference to Video Motion Control Multi-elements to video Extend Video Lip Sync Avatar Text to Audio Video to Audio Text to Speech Voice Clone Image Recognize Element Effects Effect Templates NEW Video Effects Image Generation Models Image Omni Image Generation Reference to Image Extend Image AI Multi-Shot Virtual Try-On Others Query user info Pricing Billing Info Prepaid Resource Packs Protocols Privacy Policy of API Service Terms of API Service API Service Level Agreement Image to Video Create Task POST /v1/videos/image2video cURL Copy Collapse curl --location --request POST 'https://api-singapore.klingai.com/v1/videos/image2video' \ --header 'Authorization: Bearer ' \ --header 'Content-Type: application/json' \ --data-raw '{ "model_name": "kling-v2-6", "image": "https://p2-kling.klingai.com/kcdn/cdn-kcdn112452/kling-qa-test/multi-2.png", "image_tail": "https://p2-kling.klingai.com/kcdn/cdn-kcdn112452/kling-qa-test/multi-1.png", "prompt": "Camera zooms out, the girl smiles", "negative_prompt": "", "duration": "5", "mode": "pro", "sound": "off", "callback_url": "", "external_task_id": "" }' 200 Copy Collapse { "code": 0, // Error codes; Specific definitions can be found in "Error Code" "message": "string", // Error information "request_id": "string", // Request ID, generated by the system "data": { "task_id": "string", // Task ID, generated by the system "task_info": { // Task creation parameters "external_task_id": "string" // Customer-defined task ID }, "task_status": "string", // Task status, Enum values: submitted, processing, succeed, failed "created_at": 1722769557708, // Task creation time, Unix timestamp, unit ms "updated_at": 1722769557708 // Task update time, Unix timestamp, unit ms } } 💡 Please note that in order to maintain naming consistency, the original model field has been changed to model_name. Please use this field to specify the model version in the future. We maintain backward compatibility. If you continue using the original model field, it will not affect API calls and will be equivalent to the default behavior when model_name is empty (i.e., calling the V1 model). Request Header Content-Type string Required Default to application/json Data Exchange Format Authorization string Required Authentication information, refer to API authentication Request Body model_name string Optional Default to kling-v1 Model Name Enum values： kling-v1 kling-v1-5 kling-v1-6 kling-v2-master kling-v2-1 kling-v2-1-master kling-v2-5-turbo kling-v2-6 kling-v3 image string Optional Reference Image Supports image Base64 encoding or image URL (ensure accessibility) Important: When using Base64, do NOT add any prefix like data:image/png;base64,. Submit only the raw Base64 string. Correct Base64 format: iVBORw0KGgoAAAANSUhEUgAAAAUA... Incorrect Base64 format (with data: prefix): data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUA... Supported image formats: .jpg / .jpeg / .png File size: ≤10MB, dimensions: min 300px, aspect ratio: 1:2.5 ~ 2.5:1 At least one of image or image_tail must be provided; both cannot be empty Support varies by model version and video mode. See Capability Map for details. image_tail string Optional Reference Image - End frame control Supports image Base64 encoding or image URL (ensure accessibility) Important: When using Base64, do NOT add any prefix like data:image/png;base64,. Submit only the raw Base64 string. Supported image formats: .jpg / .jpeg / .png File size: ≤10MB, dimensions: min 300px At least one of image or image_tail must be provided; both cannot be empty image_tail, dynamic_masks/static_mask, and camera_control are mutually exclusive - only one can be used at a time Support varies by model version and video mode. See Capability Map for details. multi_shot boolean Optional Default to false Whether to generate multi-shot video When true: the prompt parameter is invalid, and the first/end frame generation is not supported. When false: the shot_type and multi_prompt parameters are invalid shot_type string Optional Storyboard method Enum values： customize intelligence When multi_shot is true, this parameter is required prompt string Optional Positive text prompt 💡 The Omni model can achieve various capabilities through Prompt with elements, images, videos, and other content: Specify elements/images/videos using <<<>>> format, e.g.: <<>>, <<>>, <<>> For detailed capabilities, see: KLING Omni Model User Guide, Kling VIDEO 3.0 Omni Model User Guide Cannot exceed 2500 characters When multi_shot is false or shot_type is intelligence, this parameter must not be empty. Use <<>> to specify voice, with the sequence matching the voice_list parameter order A video generation task can reference up to 2 voices; when specifying a voice, the sound parameter must be "on" The simpler the syntax structure, the better. Example: The man<<>> said: "Hello" When voice_list is not empty and prompt references voice ID, the task will be billed as "with specified voice" Support varies by model version and video mode. See Capability Map for details. multi_prompt array Optional Information about each storyboard, such as prompts and duration Define the shot sequence number, corresponding prompt word, and duration through the index, prompt, and duration parameters, where: Supports up to 6 storyboards, with a minimum of 1 storyboard. The maximum length of the prompt for each storyboard 512 characters. The duration of each storyboard should not exceed the total duration, but should not be less than 1. The sum of the durations of all storyboards equals the total duration of the current task. Load with key:value format as follows: "multi_prompt":[ {"index":int,"prompt":"string","duration":"5"}, {"index":int,"prompt":"string","duration":"5"} ] When multi_shot is true and shot_type is customize, this parameter is required. negative_prompt string Optional Negative text prompt Cannot exceed 2500 characters It is recommended to supplement negative prompt via negative sentences within positive prompts element_list array Optional Reference Element List, based on element ID from element library Supports up to 3 reference elements The elements are categorized into video customization element (named as Video Character Elements) and image customization elements (named as Multi-Image Elements), each with distinct scopes of application. Please exercise caution in distinguishing between them. See Kling Element Library User Guide. Load with key:value format as follows: "element_list":[ { "element_id": long }, { "element_id": long } ] Support varies by model version and video mode. See Capability Map for details. ▾ Hide child attributes element_id long Required Element ID from element library voice_list array Optional List of voices referenced when generating videos A video generation task can reference up to 2 voices When voice_list is not empty and prompt references voice ID, the task will be billed as "with specified voice" voice_id is returned through the voice customization API, or use system preset voices. See Custom Voices API; NOT the voice_id of Lip-Sync API element_list and voice_list are mutually exclusive and cannot coexist Example: "voice_list":[ {"voice_id":"voice_id_1"}, {"voice_id":"voice_id_2"} ] The support range for different model versions and video modes varies. For details, see Capability Map sound string Optional Default to off Whether to generate sound when generating video Enum values： on off The support range for different model versions and video modes varies. For details, see Capability Map cfg_scale float Optional Default to 0.5 Flexibility in video generation; higher value means lower model flexibility and stronger relevance to user prompt Value range: [0, 1] kling-v2.x models do not support this parameter mode string Optional Default to std Video generation mode Enum values： std pro std: Standard Mode - basic mode, cost-effective pro: Professional Mode (High Quality) - high performance mode, better video quality Support varies by model version and video mode. See Capability Map for details. static_mask string Optional Static brush mask area (mask image created by user using motion brush) The "Motion Brush" feature includes Dynamic Brush (dynamic_masks) and Static Brush (static_mask) Supports image Base64 encoding or image URL (same format requirements as image field) Supported image formats: .jpg / .jpeg / .png Aspect ratio must match the input image (image field), otherwise task will fail Resolution of static_mask and dynamic_masks.mask must be identical, otherwise task will fail Support varies by model version and video mode. See Capability Map for details. dynamic_masks array Optional Dynamic brush configuration list Can configure multiple groups (up to 6), each containing "mask area" and "motion trajectory" sequence Support varies by model version and video mode. See Capability Map for details. ▾ Hide child attributes mask string Required Dynamic brush mask area (mask image created by user using motion brush) Supports image Base64 encoding or image URL (same format requirements as image field) Supported image formats: .jpg / .jpeg / .png Aspect ratio must match the input image (image field), otherwise task will fail Resolution of static_mask and dynamic_masks.mask must be identical, otherwise task will fail trajectories array Required Motion trajectory coordinate sequence For 5s video, trajectory length ≤77, coordinate count range: [2, 77] Coordinate system uses bottom-left corner of image as origin Note 1: More coordinate points = more accurate trajectory. 2 points = straight line between them Note 2: Trajectory direction follows input order. First coordinate is start point, subsequent coordinates are connected sequentially ▾ Hide child attributes x int Required X coordinate of trajectory point (pixel coordinate with image bottom-left as origin) y int Required Y coordinate of trajectory point (pixel coordinate with image bottom-left as origin) camera_control object Optional Camera movement control protocol (if not specified, model will intelligently match based on input text/images) Support varies by model version and video mode. See Capability Map for details. ▾ Hide child attributes type string Required Predefined camera movement type Enum values： simple down_back forward_up right_turn_forward left_turn_forward simple: Simple camera movement, can choose one of six options in "config" down_back: Camera descends and moves backward ➡️ Pan down and zoom out. config parameter not required forward_up: Camera moves forward and tilts up ➡️ Zoom in and pan up. config parameter not required right_turn_forward: Rotate right then move forward ➡️ Right rotation advance. config parameter not required left_turn_forward: Rotate left then move forward ➡️ Left rotation advance. config parameter not required config object Optional Contains 6 fields to specify camera movement in different directions Required when type is "simple"; leave empty for other types Choose only one parameter to be non-zero; rest must be 0 ▾ Hide child attributes horizontal float Optional Horizontal movement - camera translation along x-axis Value range: [-10, 10]. Negative = left, Positive = right vertical float Optional Vertical movement - camera translation along y-axis Value range: [-10, 10]. Negative = down, Positive = up pan float Optional Horizontal pan - camera rotation around y-axis Value range: [-10, 10]. Negative = rotate left, Positive = rotate right tilt float Optional Vertical tilt - camera rotation around x-axis Value range: [-10, 10]. Negative = tilt down, Positive = tilt up roll float Optional Roll - camera rotation around z-axis Value range: [-10, 10]. Negative = counterclockwise, Positive = clockwise zoom float Optional Zoom - controls camera focal length change, affects field of view Value range: [-10, 10]. Negative = longer focal length (narrower FOV), Positive = shorter focal length (wider FOV) duration string Optional Default to 5 Video duration in seconds Enum values： 3 4 5 6 7 8 9 10 11 12 13 14 15 Support varies by model version and video mode. See Capability Map for details. watermark_info object Optional Whether to generate watermarked results simultaneously Defined by the enabled parameter, format: "watermark_info": { "enabled": boolean } true: generate watermarked result, false: do not generate Custom watermarks are not currently supported callback_url string Optional Callback notification URL for task result. If configured, server will notify when task status changes. For specific message schema, see Callback Protocol external_task_id string Optional Customized Task ID Will not overwrite system-generated task ID, but supports querying task by this ID Must be unique within a single user account Scenario invocation examples Image to video with multi-shot curl --location 'https://xxx/v1/videos/image2video' \ --header 'Authorization: Bearer xxx' \ --header 'Content-Type: application/json' \ --data '{ "model_name": "kling-v3", "image": "xxx", "prompt": "", "multi_shot": "true", "shot_type": "customize", "multi_prompt": [ { "index": 1, "prompt": "Two friends talking under a streetlight at night. Warm glow, casual poses, no dialogue.", "duration": "2" }, { "index": 2, "prompt": "A runner sprinting through a forest, leaves flying. Low-angle shot, focus on movement.", "duration": "3" }, { "index": 3, "prompt": "A woman hugging a cat, smiling. Soft sunlight, cozy home setting, emphasize warmth.", "duration": "3" }, { "index": 4, "prompt": "A door creaking open, shadowy hallway. Dark tones, minimal details, eerie mood.", "duration": "3" }, { "index": 5, "prompt": "A man slipping on a banana peel, shocked expression. Exaggerated pose, bright colors.", "duration": "3" }, { "index": 6, "prompt": "A sunset over mountains, small figure walking away. Wide angle, peaceful atmosphere.", "duration": "1" } ], "negative_prompt": "", "duration": "15", "mode": "pro", "sound": "on", "callback_url": "", "external_task_id": "" }' Image to video with element curl --location 'https://api-singapore.klingai.com/v1/images/generations' \ --header 'Authorization: Bearer xxx' \ --header 'Content-Type: application/json' \ --data '{ "model_name": "kling-v3", "prompt": "Merge all the characters from the images into the <<>> diagram", "element_list": [ { "element_id": "160" }, { "element_id": "161" }, { "element_id": "159" } ], "image": "xxx", "resolution": "2k", "n": "9", "aspect_ratio": "3:2", "external_task_id": "", "callback_url": "" }' curl --location 'https://xxx/v1/videos/text2video' \ --header 'Authorization: Bearer xxx' \ --header 'Content-Type: application/json' \ --data '{ "model_name": "kling-v3", "prompt": "", "multi_prompt": [ { "index": 1, "prompt": "Two friends talking under a streetlight at night. Warm glow, casual poses, no dialogue.", "duration": "2" }, { "index": 2, "prompt": "A runner sprinting through a forest, leaves flying. Low-angle shot, focus on movement.", "duration": "3" }, { "index": 3, "prompt": "A woman hugging a cat, smiling. Soft sunlight, cozy home setting, emphasize warmth.", "duration": "3" }, { "index": 4, "prompt": "A door creaking open, shadowy hallway. Dark tones, minimal details, eerie mood.", "duration": "3" }, { "index": 5, "prompt": "A man slipping on a banana peel, shocked expression. Exaggerated pose, bright colors.", "duration": "3" }, { "index": 6, "prompt": "A sunset over mountains, small figure walking away. Wide angle, peaceful atmosphere.", "duration": "1" } ], "multi_shot": true, "shot_type": "customize", "duration": "15", "mode": "pro", "sound": "on", "aspect_ratio": "9:16", "callback_url": "", "external_task_id": "" }' Generate video with voice control curl --location 'https://api-singapore.klingai.com/v1/videos/image2video/' \ --header 'Authorization: Bearer {Replace your token}' \ --header 'Content-Type: application/json; charset=utf-8' \ --data '{ "model_name": "kling-v2-6", "image": "Replace the URL of image", "prompt": "<<>>Ask the people in the picture to say the following words, '\''Welcome everyone'\''", //If a specific dialogue needs to be enclosed in quotation marks "voice_list": [ { "voice_id": "Replace the ID of voice" } ], "duration": "5", "mode": "pro", "sound": "on", "callback_url": "", "external_task_id": "" }' Query Task (Single) GET /v1/videos/image2video/{id} cURL Copy Collapse curl --request GET \ --url https://api-singapore.klingai.com/v1/videos/image2video/{task_id} \ --header 'Authorization: Bearer ' 200 Copy Collapse { "code": 0, // Error codes; Specific definitions can be found in "Error Code" "message": "string", // Error information "request_id": "string", // Request ID, generated by the system, is used to track requests and troubleshoot problems "data": { "task_id": "string", // Task ID, generated by the system "task_status": "string", // Task status, Enum values: submitted, processing, succeed, failed "task_status_msg": "string", // Task status information, displaying the failure reason when the task fails (such as triggering the content risk control of the platform, etc.) "watermark_info": { "enabled": boolean }, "task_result": { "videos": [ { "id": "string", // Generated video ID; globally unique "url": "string", // URL for generating videos (To ensure information security, generated images/videos will be cleared after 30 days. Please make sure to save them promptly.) "watermark_url": "string", // Watermarked video download URL, anti-leech format "duration": "string" // Total video duration, unit: s } ] }, "task_info": { // Task creation parameters "external_task_id": "string" // Customer-defined task ID }, "final_unit_deduction": "string", // The deduction units of task "created_at": 1722769557708, // Task creation time, Unix timestamp, unit: ms "updated_at": 1722769557708 // Task update time, Unix timestamp, unit: ms } } Request Header Content-Type string Required Default to application/json Data Exchange Format Authorization string Required Authentication information, refer to API authentication Path Parameters task_id string Optional Task ID for image to video Request path parameter, fill value directly in request path Choose one between task_id and external_task_id for querying external_task_id string Optional Customized Task ID for image to video The external_task_id provided when creating the task Choose one between task_id and external_task_id for querying Query Task (List) GET /v1/videos/image2video cURL Copy Collapse curl --request GET \ --url 'https://api-singapore.klingai.com/v1/videos/image2video?pageNum=1&pageSize=30' \ --header 'Authorization: Bearer ' 200 Copy Collapse { "code": 0, // Error codes; Specific definitions can be found in Error codes "message": "string", // Error information "request_id": "string", // Request ID, generated by the system, to track requests and troubleshoot problems "data": [ { "task_id": "string", // Task ID, generated by the system "task_status": "string", // Task status, Enum values: submitted, processing, succeed, failed "task_status_msg": "string", // Task status information, displaying the failure reason when the task fails (such as triggering the content risk control of the platform, etc.) "task_info": { // Task creation parameters "external_task_id": "string" // Customer-defined task ID }, "task_result": { "videos": [ { "id": "string", // Generated video ID; globally unique "url": "string", // URL for generating videos (To ensure information security, generated images/videos will be cleared after 30 days. Please make sure to save them promptly.) "watermark_url": "string", // Watermarked video download URL, anti-leech format "duration": "string" // Total video duration, unit: s (seconds) } ] }, "watermark_info": { "enabled": boolean }, "final_unit_deduction": "string", // The deduction units of task "created_at": 1722769557708, // Task creation time, Unix timestamp, unit: ms "updated_at": 1722769557708 // Task update time, Unix timestamp, unit: ms } ] } Request Header Content-Type string Required Default to application/json Data Exchange Format Authorization string Required Authentication information, refer to API authentication Query Parameters pageNum int Optional Default to 1 Page number Value range: [1, 1000] pageSize int Optional Default to 30 Data volume per page Value range: [1, 500] Previous chapter：Text to Video Next chapter：Reference to Video Create Task Scenario invocation examples Query Task (Single) Query Task (List) The Kling 3.0 Series Models API is Now Fully Available – All in One, One for All！ Models Available in This Release Kling 3.0 Motion Control, Kling Video 3.0, Kling Video 3.0 Omni, Kling Image 3.0, Kling Image 3.0 Omni Refer to Key Highlights of the Models 3.0 All-in-One: A unified model for multi-modal input and output. Most powerful consistency across the universe: Subject consistency (supports cameo, subject with voice control, i2v + subject) and text consistency. Narrative control at your fingertips: More freedom, precision, and control—up to 15 seconds long, video scene cuts, ultra-high-definition storyboards/images, custom seconds. Upgraded native audio-visual output: Supports multiple speakers and languages (with accents). Kling 3.0 Motion Control Consistent Facial Identity from any angle Complex Emotions faithfully reproduced High fidelity Restoration, Even with Face Occlusions Consistent Facial Clarity Across Dynamic Framing User Guide -> Kling Video 3.0 Compared to 2.6, expected improvements: Supports subject upload in I2V scenarios for enhanced consistency Significant improvement in multi-character referencing, especially for three-person scenarios Supports Japanese, Korean, and Spanish in addition to Chinese and English Capable of generating certain dialects and accents Better distinction and control over different types of audio (speech, sound effects, BGM) Improved text retention in I2V scenarios Supports scene transitions, with up to 6 shots and customizable storyboarding User Guide -> Kling Video 3.0 Omni Compared to O1, expected improvements: Native audio-visual synchronization Supports video subject creation Further improved consistency in reference-based tasks, especially for characters and products Combined capabilities of reference + storyboarding + audio-visual sync significantly enhance usability Supports scene transitions, with up to 6 shots Extended generation duration up to 15 seconds User Guide -> Kling Image 3.0 Highly consistent feature retention Precise response to detail modifications Accurate control over style and tone Rich imaginative capabilities User Guide -> Kling Image 3.0 Omni Enhanced narrative sense New storyboard image set generation, retaining reference image features with scene relevance Direct output of 2K/4K ultra-high-definition images Further improved detail consistency User Guide -> Thank you for your support and understanding! I Got It