### Start Dubbing API Request Example Source: https://api.a2e.ai/start-dubbing-12138830e0 This example demonstrates how to initiate an AI dubbing process. It requires specifying the audio file URL, source and target languages, number of speakers, background audio drop setting, and expected duration. The response includes a status code and data containing details of the submitted job. ```json { "name": "test", "source_url": "https://dh24as48lv9ce.cloudfront.net/adam2eve/stable/user_voice_clone/b89f5b2e-2c7a-4de5-89b4-17ffee2799b6/audio.WAV", "current_status": "sent", "source_lang": "auto", "target_lang": "en", "num_speakers": 1, "drop_background_audio": false, "duration": 51, "result_url": "", "faild_message": "", "_id": "66ea4dd87db10c73fa29b570", "user_id": "665da3d7bcf6ab778bad0f6a", "createdAt": "2024-09-18T03:49:44.704Z", "updatedAt": "2024-09-18T03:49:44.704Z" } ``` -------------------------------- ### POST /api/v1/talkingPhoto/start Source: https://api.a2e.ai/start-a-task-18756987e0 Starts a new task to create an AI-generated talking photo. This endpoint requires an image URL, an audio URL, and descriptive prompts to guide the AI. ```APIDOC ## POST /api/v1/talkingPhoto/start ### Description Starts a new task to create an AI-generated talking photo. This endpoint requires an image URL, an audio URL, and descriptive prompts to guide the AI. ### Method POST ### Endpoint /api/v1/talkingPhoto/start ### Parameters #### Request Body - **name** (string) - Required - A name for the talking photo task. - **image_url** (string) - Required - URL of a photo for talking/singing. - **audio_url** (string) - Required - URL of an audio file as talking/singing source. - **duration** (integer) - Optional - Duration of the animating talking/singing video in seconds (1-10 seconds, default: 3). - **prompt** (string) - Required - Text prompt describing the desired talking/singing style, mood, or characteristics. - **negative_prompt** (string) - Required - Negative prompt specifying what should be avoided in the talking/singing generation. ### Request Example ```json { "name": "My first AI Talking Photo", "image_url": "https://example.com/8857f31c-4873-4e12-aff3-dbc5640512e7.JPG", "audio_url": "https://example.com/zh.WAV", "duration": 3, "prompt": "speaking, looking at the camera, detailed eyes, clear teeth, static view point, still background, elegant, clear facial features, stable camera, professional shooting angle", "negative_prompt": "vivid colors, overexposed, flickering, blurry details, subtitles, logo, style, artwork, painting, image, static, overall grayish, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless person, cluttered background, three legs, crowded background, walking backwards" } ``` ### Response #### Success Response (200) - **code** (integer) - 0 is OK. - **data** (object) - Contains details of the generated task. - **_id** (string) - The ID of the image singing task. - **name** (string) - The name of the task. - **image_url** (string) - URL of the input image. - **audio_url** (string) - URL of the input audio. - **duration** (integer) - Duration of the generated video. - **current_status** (string) - The status of the record (initialized, sent, pending, processing, completed, failed). - **coins** (integer) - Number of coins used for the task. - **createdAt** (string) - Timestamp of task creation. - **failed_message** (string) - Message if the task failed. - **failed_code** (string) - Error code if the task failed. - **result_url** (string) - URL of the generated talking photo video (if completed). - **prompt** (string) - The prompt used for generation. - **negative_prompt** (string) - The negative prompt used for generation. #### Response Example ```json { "code": 0, "data": { "_id": "60d5ecf1b37f1b001f8e4f5d", "name": "My first AI Talking Photo", "image_url": "https://example.com/8857f31c-4873-4e12-aff3-dbc5640512e7.JPG", "audio_url": "https://example.com/zh.WAV", "duration": 3, "current_status": "initialized", "coins": 10, "createdAt": "2023-10-27T10:00:00Z", "failed_message": "", "failed_code": "", "result_url": "", "prompt": "speaking, looking at the camera, detailed eyes, clear teeth, static view point, still background, elegant, clear facial features, stable camera, professional shooting angle", "negative_prompt": "vivid colors, overexposed, flickering, blurry details, subtitles, logo, style, artwork, painting, image, static, overall grayish, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless person, cluttered background, three legs, crowded background, walking backwards" } } ``` ``` -------------------------------- ### Start a Task API Source: https://api.a2e.ai/start-a-task-18756987e0 This section details the API endpoint for starting a new task. ```APIDOC ## POST /websites/api_a2e_ai ### Description This endpoint initiates a new task within the system. It requires specific parameters to define the task details. ### Method POST ### Endpoint /websites/api_a2e_ai ### Parameters #### Path Parameters None #### Query Parameters None #### Request Body - **task_name** (string) - Required - The name of the task to be started. - **task_parameters** (object) - Optional - Additional parameters for the task. - **param1** (string) - Optional - Description of param1. - **param2** (integer) - Optional - Description of param2. ### Request Example ```json { "task_name": "data_processing", "task_parameters": { "input_file": "/path/to/data.csv", "output_format": "json" } } ``` ### Response #### Success Response (200) - **task_id** (string) - A unique identifier for the initiated task. - **status** (string) - The initial status of the task (e.g., "pending", "running"). #### Response Example ```json { "task_id": "task_12345abc", "status": "pending" } ``` ``` -------------------------------- ### Start Talking Photo Task (OpenAPI) Source: https://api.a2e.ai/start-a-task-18756987e0 This OpenAPI specification defines the 'start' endpoint for the Talking Photo API. It uses a POST request to initiate the creation of an animated photo. Key inputs include image and audio URLs, desired duration, and prompts for style and content, with specific requirements for these parameters. ```yaml openapi: 3.0.1 info: title: '' description: '' version: 1.0.0 paths: /api/v1/talkingPhoto/start: post: summary: Start a Task deprecated: false description: '' tags: - Talking Photo parameters: [] requestBody: content: application/json: schema: type: object properties: name: type: string description: A name of talking photo task image_url: type: string description: URL of a photo for talking/singing audio_url: type: string description: URL of a audio file as talking/singing source duration: type: integer description: >- Duration of the animating talking/singing video in seconds (1-10 seconds, default: 3) prompt: type: string description: >- Text prompt describing the desired talking/singing style, mood, or characteristics negative_prompt: type: string description: >- Negative prompt specifying what should be avoided in the talking/singing generation required: - name - image_url - audio_url - prompt - negative_prompt x-apidog-orders: - name - image_url - audio_url - duration - prompt - negative_prompt example: name: My first AI Talking Photo image_url: https://example.com/8857f31c-4873-4e12-aff3-dbc5640512e7.JPG audio_url: https://example.com/zh.WAV duration: 3 prompt: >- speaking, looking at the camera, detailed eyes, clear teeth, static view point, still background, elegant, clear facial features, stable camera, professional shooting angle negative_prompt: >- vivid colors, overexposed, flickering, blurry details, subtitles, logo, style, artwork, painting, image, static, overall grayish, worst quality, low quality, JPEG compression artifacts, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless person, cluttered background, three legs, crowded background, walking backwards responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer description: 0 is OK data: type: object properties: _id: type: string description: The ID of the image singing task. name: type: string image_url: type: string audio_url: type: string duration: type: integer current_status: type: string description: |- The status of the record. - ``initialized``: initialization - ``sent``: sent to algorithm - ``pending``: in algorithm queue - ``processing``: being processed - ``completed``: completed - ``failed``: algorithm failed coins: type: integer createdAt: type: string failed_message: type: string failed_code: type: string result_url: type: string prompt: type: string negative_prompt: type: string required: - _id - name - image_url - audio_url - duration - current_status - coins - createdAt - failed_message - failed_code ``` -------------------------------- ### Start Product Avatar Source: https://api.a2e.ai/start-product-avatar-20861897e0 Initiates the product avatar generation process. ```APIDOC ## POST /api/v1/productAvatar/start ### Description Starts the product avatar generation process. This endpoint is part of the Product Avatar API. ### Method POST ### Endpoint /api/v1/productAvatar/start ### Parameters #### Path Parameters None #### Query Parameters None #### Request Body None specified in the OpenAPI schema. ### Request Example ```json { "example": "No request body defined" } ``` ### Response #### Success Response (200) - **code** (integer) - 0 is OK - **data** (object) - Contains data related to the product avatar process. The specific properties are not detailed in the schema. #### Response Example ```json { "code": 0, "data": {} } ``` ``` -------------------------------- ### Example API Request Payload Source: https://api.a2e.ai/generate-ai-avatar-videos-12138800e0 This example shows a complete request payload for generating an AI video. It includes essential parameters like title, anchor ID, audio source, resolution, and optional settings for web background and people dimensions, as well as captioning configuration. ```yaml example: title: My first AI video anchor_id: 660556b3cd492168141926d3 anchor_type: 1 back_id: 62a6d3e56c209514b155b12b audioSrc: >- https://speech_cdn.ai-anchor.com/dubbing_stable/pyK1dvqcDKpKJo1IcEPm_9714_fr.mp3 resolution: 1080 web_bg_width: 853 web_bg_height: 480 web_people_width: 270 web_people_height: 480 web_people_x: 292 web_people_y: 0 isSkipRs: true isCaptionEnabled: true captionAlign: language: en-US PrimaryColour: rgba(247, 89, 171, 1) OutlineColour: rgba(0, 0, 0, 1) BorderStyle: 4 BackColour: rgba(146, 84, 222, 1) FontName: AaFengKuangYuanShiRen Fontsize: 50 subtitle_position: 0.3 ``` -------------------------------- ### OpenAPI Specification for Start Product Avatar Source: https://api.a2e.ai/start-product-avatar-20861897e0 This YAML defines the OpenAPI 3.0.1 specification for the 'Start Product Avatar' POST endpoint. It includes details about the request method, summary, tags, parameters, responses with a 200 success code, and security schemes. The server URLs for global and China deployments are also specified. ```yaml openapi: 3.0.1 info: title: '' description: '' version: 1.0.0 paths: /api/v1/productAvatar/start: post: summary: Start Product Avatar deprecated: false description: '' tags: - Product Avatar parameters: [] responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer description: 0 is OK data: type: object properties: {} x-apidog-orders: [] x-apidog-orders: - code - data required: - code - data headers: {} x-apidog-name: Success security: - bearer: [] x-apidog-folder: Product Avatar x-apidog-status: developing x-run-in-apidog: https://app.apidog.com/web/project/751853/apis/api-20861897-run components: schemas: {} securitySchemes: bearer: type: http scheme: bearer servers: - url: https://video.a2e.ai description: Global Server - url: https://video.a2e.com.cn description: China Server security: - bearer: [] ``` -------------------------------- ### GET /api/v1/userImage2Video/{_id} Source: https://api.a2e.ai/check-status-of-one-task-14771261e0 Retrieves the status of a previously started image-to-video task using its unique identifier. ```APIDOC ## GET /api/v1/userImage2Video/{_id} ### Description Check the status of a specific image-to-video task using its unique ID. ### Method GET ### Endpoint /api/v1/userImage2Video/{_id} ### Parameters #### Path Parameters - **_id** (string) - Required - The unique identifier for the task, obtained from the `/api/v1/userImage2Video/start` endpoint. ### Request Example (No request body for GET requests) ### Response #### Success Response (200) - **code** (integer) - Describes the result of the operation. 0 indicates success. - **data** (object) - Contains the task details. - **_id** (string) - The task's unique identifier. - **name** (string) - The name associated with the task. - **image_url** (string) - The original image URL provided for the task. - **current_status** (string) - The current status of the task (e.g., 'sent', 'pending', 'completed'). - **coins** (integer) - The number of coins consumed by the task. - **createdAt** (string) - The timestamp when the task was initiated. - **failed_message** (string) - A message if the task failed. - **failed_code** (string) - A code indicating the reason for failure. - **result_url** (string) - The URL of the generated video, available upon task completion. - **trace_id** (string) - A unique identifier for tracing the request. #### Response Example ```json { "code": 0, "data": { "_id": "67d29023dd27a536fdf6e809", "name": "Test name", "image_url": "https://example.com/524f2258-c5a0-4bb2-9003-5e4740a2d376.png", "current_status": "completed", "coins": 100, "createdAt": "2025-03-13T07:58:27.863Z", "failed_message": "", "failed_code": "", "result_url": "https://example.com/adam2eve/beta/users/665da3d7bcf6ab778bad0f6a/f9362ad5-1186-4bf5-a1d8-7314ea9ba47f.mp4" }, "trace_id": "f53cfb3c-1a42-4f07-b8e3-5020244b1e04" } ``` ``` -------------------------------- ### Get R2 Upload Presigned URL Request Example (OpenAPI) Source: https://api.a2e.ai/get-r2-upload-presigned-url-19773786e0 This OpenAPI specification defines the 'Get R2 Upload Presigned URL' POST request. It includes the schema for the request body, which requires a 'key' (file path/name), and the schema for the successful response, which provides an 'uploadUrl', 'key', and 'expiresIn'. ```yaml openapi: 3.0.1 info: title: '' description: '' version: 1.0.0 paths: /api/v1/r2/get_upload_presigned_url: post: summary: Get R2 Upload Presigned URL deprecated: false description: >- 1. Call this API to obtain a presigned URL 2. Use the received `uploadUrl` to upload the file via an HTTP PUT request 3. After successful upload, the file will be stored in the specified R2 bucket at the path indicated by `data.key` #### Notes - This API consumes 1 coin from the user's balance - The presigned URL is valid for 300 seconds by default; a new URL must be requested after expiration - Uploaded files are stored in the user's dedicated directory: `environment/userId/storage/filename` tags: - Miscellaneous parameters: [] requestBody: content: application/json: schema: type: object properties: key: type: string description: >- File path/name in storage, e.g., folder/subfolder/test.mp4 or just test.mp4 required: - key x-apidog-orders: - key example: key: path/test.mp4 responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer data: type: object properties: uploadUrl: type: string description: | Presigned upload URL for direct file upload key: type: string description: >- File path/name in storage, e.g., folder/subfolder/test.mp4 or just test.mp4 expiresIn: type: integer description: URL validity period (seconds) required: - uploadUrl - key - expiresIn x-apidog-orders: - uploadUrl - key - expiresIn trace_id: type: string required: - code - data - trace_id x-apidog-orders: - code - data - trace_id example: code: 0 data: uploadUrl: >- https://a2e-prod-jumpy.249f5378ffb8a0786e403d44c62e5459.r2.cloudflarestorage.com/beta/1avdcdd7bcf6ab778bad1234/storage/path/test.mp4?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=774ea6b5cfe6a35a7bfa721eee24b0a5%2F20250801%2Fauto%2Fs3%2Faws4_request&X-Amz-Date=20250801T092045Z&X-Amz-Expires=300&X-Amz-Signature=2e5ee8be0b46a42c58f67eb8ff70f3b8e99e75466860cb8e9511f3f718bcc45f&X-Amz-SignedHeaders=host&x-amz-checksum-crc32=AAAAAA%3D%3D&x-amz-sdk-checksum-algorithm=CRC32&x-id=PutObject key: beta/665da3d7bcf6ab778bad0f6a/storage/test.mp4 bucket: a2e-prod-jumpy expiresIn: 300 trace_id: 14992ffe-68b3-44ef-973e-c72c1fe7c34c headers: {} x-apidog-name: Success security: - bearer: [] x-apidog-folder: Miscellaneous x-apidog-status: released x-run-in-apidog: https://app.apidog.com/web/project/751853/apis/api-19773786-run components: schemas: {} securitySchemes: bearer: type: http scheme: bearer servers: - url: https://video.a2e.ai description: Global Server - url: https://video.a2e.com.cn description: China Server security: - bearer: [] ``` -------------------------------- ### Face Swap Task Management API Source: https://api.a2e.ai/llms Endpoints for starting and managing face swap tasks, including getting task status, records, and details. ```APIDOC ## POST /api/v1/faceSwap/task/start ### Description Start a face swap task by providing the name, face URL, and video URL. ### Method POST ### Endpoint /api/v1/faceSwap/task/start ### Parameters #### Request Body - `taskName` (string) - Required - A name for the face swap task. - `faceUrl` (string) - Required - The URL of the face image. - `videoUrl` (string) - Required - The URL of the video to perform the face swap on. ### Request Example ```json { "example": { "taskName": "My First Face Swap", "faceUrl": "https://example.com/faces/another_face.jpg", "videoUrl": "https://example.com/videos/target_video.mp4" } } ``` ### Response #### Success Response (200) - `taskId` (string) - The unique identifier for the started face swap task. - `status` (string) - The initial status of the task. #### Response Example ```json { "example": { "taskId": "faceswap_task_mno789", "status": "pending" } } ``` ``` ```APIDOC ## GET /api/v1/faceSwap/task/status/{taskId} ### Description Retrieve the status of a user's face swap task. ### Method GET ### Endpoint /api/v1/faceSwap/task/status/{taskId} ### Parameters #### Path Parameters - `taskId` (string) - Required - The unique identifier of the face swap task. ### Request Example ```json { "example": "GET /api/v1/faceSwap/task/status/faceswap_task_mno789" } ``` ### Response #### Success Response (200) - `status` (string) - The current status of the face swap task (e.g., 'processing', 'completed', 'failed'). - `progress` (number) - The progress of the task in percentage (0-100). #### Response Example ```json { "example": { "status": "processing", "progress": 75 } } ``` ``` ```APIDOC ## GET /api/v1/faceSwap/task/records ### Description Retrieve a list of user face swap task records. ### Method GET ### Endpoint /api/v1/faceSwap/task/records ### Parameters #### Query Parameters - `limit` (integer) - Optional - Maximum number of records to return. - `offset` (integer) - Optional - Number of records to skip (for pagination). ### Request Example ```json { "example": "GET /api/v1/faceSwap/task/records?limit=10&offset=0" } ``` ### Response #### Success Response (200) - `records` (array) - A list of face swap task records. - `taskId` (string) - The unique identifier for the task. - `taskName` (string) - The name of the task. - `status` (string) - The status of the task. - `createdAt` (string) - Timestamp of task creation. #### Response Example ```json { "example": { "records": [ { "taskId": "faceswap_task_mno789", "taskName": "My First Face Swap", "status": "completed", "createdAt": "2023-10-27T12:00:00Z" } ] } } ``` ``` ```APIDOC ## GET /api/v1/faceSwap/task/{taskId} ### Description Retrieve the details of a specific user face swap task by its ID. ### Method GET ### Endpoint /api/v1/faceSwap/task/{taskId} ### Parameters #### Path Parameters - `taskId` (string) - Required - The unique identifier of the face swap task. ### Request Example ```json { "example": "GET /api/v1/faceSwap/task/faceswap_task_mno789" } ``` ### Response #### Success Response (200) - `taskId` (string) - The unique identifier for the task. - `taskName` (string) - The name of the task. - `faceUrl` (string) - The URL of the face image used. - `videoUrl` (string) - The URL of the video used. - `status` (string) - The status of the task. - `resultUrl` (string) - The URL of the completed face swap video (if available). - `createdAt` (string) - Timestamp of task creation. - `updatedAt` (string) - Timestamp of the last update. #### Response Example ```json { "example": { "taskId": "faceswap_task_mno789", "taskName": "My First Face Swap", "faceUrl": "https://example.com/faces/another_face.jpg", "videoUrl": "https://example.com/videos/target_video.mp4", "status": "completed", "resultUrl": "https://cdn.a2e.ai/results/faceswap_task_mno789.mp4", "createdAt": "2023-10-27T12:00:00Z", "updatedAt": "2023-10-27T13:00:00Z" } } ``` ``` ```APIDOC ## DELETE /api/v1/faceSwap/task/{taskId} ### Description Delete a specific face swap task record by its ID. ### Method DELETE ### Endpoint /api/v1/faceSwap/task/{taskId} ### Parameters #### Path Parameters - `taskId` (string) - Required - The unique identifier of the face swap task to delete. ### Request Example ```json { "example": "DELETE /api/v1/faceSwap/task/faceswap_task_mno789" } ``` ### Response #### Success Response (200) - `status` (string) - The status of the operation (e.g., 'deleted'). #### Response Example ```json { "example": { "status": "deleted" } } ``` ``` -------------------------------- ### POST /api/v1/talkingVideo/start Source: https://api.a2e.ai/start-a-task-21441363e0 Starts a new talking video generation task. This endpoint takes parameters such as video URL, audio URL, and prompts to create a customized talking video. ```APIDOC ## POST /api/v1/talkingVideo/start ### Description Starts a new talking video generation task. This endpoint takes parameters such as video URL, audio URL, and prompts to create a customized talking video. ### Method POST ### Endpoint /api/v1/talkingVideo/start ### Parameters #### Request Body - **name** (string) - Required - Name of the talking video task - **video_url** (string) - Required - URL of the source video - **audio_url** (string) - Required - audio URL - **prompt** (string) - Required - Generation prompt - **negative_prompt** (string) - Required - Negative prompt to avoid unwanted features - **duration** (integer) - Optional - Duration of the animating talking/singing video in seconds (1-10 seconds, default: 3) ### Request Example ```json { "name": "My Talking Video", "video_url": "https://prod-tos.avatar2everyone.com/adam2eve/stable/user_origin_avatar/20250119/efff01ef-804b-4fe3-b104-8c8790d2b51b.mp4", "audio_url": "https://7days-tos.a2e.com.cn/tts3party_cache/stable/el/stable_7e3e8c030260f0cc3fcfdd0d791d8917/526a79e7a6d3ffebbfbcddeb9e6bfb06.mp3", "duration": 5, "prompt": "Make this person smile and speak", "negative_prompt": "blurry, distorted" } ``` ### Response #### Success Response (200) - **code** (integer) - 0 is OK - **data** (object) - Task details - **_id** (string) - The ID of the image singing task. - **name** (string) - Task name. - **image_url** (string) - URL of the generated image. - **audio_url** (string) - URL of the audio used. - **duration** (integer) - Duration of the video. - **current_status** (string) - The status of the record. (e.g., `initialized`, `sent`, `pending`, `processing`, `completed`, `failed`) - **coins** (integer) - Coins used for the task. - **createdAt** (string) - Timestamp of creation. - **failed_message** (string) - Message if the task failed. - **failed_code** (string) - Code if the task failed. - **result_url** (string) - URL of the final generated video. - **prompt** (string) - The prompt used for generation. - **negative_prompt** (string) - The negative prompt used. - **trace_id** (string) - Trace ID for the request. #### Response Example ```json { "code": 0, "data": { "_id": "65a9f0c1e1b3f7c2a8e0e8f8", "name": "My Talking Video", "image_url": "https://example.com/image.jpg", "audio_url": "https://7days-tos.a2e.com.cn/tts3party_cache/stable/el/stable_7e3e8c030260f0cc3fcfdd0d791d8917/526a79e7a6d3ffebbfbcddeb9e6bfb06.mp3", "duration": 5, "current_status": "initialized", "coins": 10, "createdAt": "2023-01-15T10:30:00Z", "failed_message": "", "failed_code": "", "result_url": "", "prompt": "Make this person smile and speak", "negative_prompt": "blurry, distorted" }, "trace_id": "trace-12345" } ``` ``` -------------------------------- ### POST /api/v1/userImage2Video/start Source: https://api.a2e.ai/start-image-to-video-14770503e0 Initiates an image-to-video task. This endpoint allows users to generate a 5-second, 720p video from a given image, with a focus on detailed facial features. The process typically completes within 10 minutes under normal conditions. ```APIDOC ## POST /api/v1/userImage2Video/start ### Description Initiate an image-to-video task. Our model produces a 5 seconds long high-quality 720p videos. Our image-to-video model is specifically optimized to generate highly detailed facial features. Under normal circumstances, a task will be completed within 10 minutes, provided there is no queue. ### Method POST ### Endpoint /api/v1/userImage2Video/start ### Parameters #### Request Body - **name** (string) - Required - The name associated with the request. - **image_url** (string) - Required - The image url for the video generation. Use `/api/v1/tos/transferToStorage` if your image url is unstable to access. - **prompt** (string) - Required - The prompt for your i2v task. e.g. `the person is speaking. Looking at the camera. detailed eyes, clear teeth,static camera view point, still background` - **negative_prmpt** (string) - Required - The negative prompt. e.g. `six fingers, bad hands, lowres, low quality, worst quality, moving camera view point, still image` ### Request Example ```json { "name": "Test name", "image_url": "https://example.com/524f2258-c5a0-4bb2-9003-5e4740a2d376.png", "prompt": "the person is speaking. Looking at the camera. detailed eyes, clear teeth, static view point, still background", "negative_prompt": "six fingers, bad hands, lowres, low quality, worst quality, moving view point, static image" } ``` ### Response #### Success Response (200) - **code** (integer) - 0 is OK - **data** (object) - Contains the result of the video generation task. - **_id** (string) - The unique identifier for the task. - **name** (string) - The name associated with the request. - **image_url** (string) - The URL of the input image. - **current_status** (string) - The current status of the task (e.g., 'sent'). - **coins** (integer) - The number of coins consumed for the task. - **createdAt** (string) - The timestamp when the task was created. - **failed_message** (string) - Message if the task failed. - **failed_code** (string) - Code if the task failed. - **trace_id** (string) - A unique identifier for tracing the request. #### Response Example ```json { "code": 0, "data": { "_id": "67d29023dd27a536fdf6e809", "name": "Test name", "image_url": "https://example.com/524f2258-c5a0-4bb2-9003-5e4740a2d376.png", "prompt": "the person is speaking. Looking at the camera. detailed eyes, clear teeth,static camera view point, still background", "negative_prompt": "six fingers, bad hands, lowres, low quality, worst quality, moving camera view point, still image", "current_status": "sent", "coins": 100, "createdAt": "2025-03-13T07:58:27.863Z", "failed_message": "", "failed_code": "" }, "trace_id": "a1ae4185-7929-4fe1-8903-13a41cc072fd" } ``` ``` -------------------------------- ### GET /api/v1/anchor/character_list Source: https://api.a2e.ai/list-one-or-all-avatars-18342996e0 Retrieves a list of all uploaded and system-provided avatars. You can optionally filter by a specific user_video_twin_id to get details for a single avatar. ```APIDOC ## GET /api/v1/anchor/character_list ### Description Return all the avatars that are uploaded by users and provided by the system. Provide user_video_twin_id to query for one avatar. Leave user_video_twin_id empty to get records of all avatars. Use the _id as the id for using "/api/v1/video/generate". ### Method GET ### Endpoint /api/v1/anchor/character_list ### Parameters #### Query Parameters - **user_video_twin_id** (string) - Optional - Returned as `_id` by `/api/v1/userVideoTwin/startTraining`. The ID of the custom created avatar being trained. Leave this empty to get all avatars. - **type** (string) - Optional - Avatar Type (custom or default: whether it is uploaded by a user or provided by the system) ### Request Example ```json { "example": "No request body needed for GET request." } ``` ### Response #### Success Response (200) - **code** (integer) - 0 is OK - **data** (array) - List of avatars. - **type** (string) - Avatar Type (custom or default: whether it is uploaded by a user or provided by the system) - **_id** (string) - The ID to use for video generation (/api/v1/video/generate) - **createdAt** (string) - Creation timestamp of the avatar. - **isExclusive** (boolean) - Indicates if the avatar is exclusive. - **background_img** (string) - Background image of the avatar. - **background_color** (string) - Background color of the avatar. The presence of either `background_img` or `background_color` is sufficient for image matting (or background removal). - **base_video** (string) - The origin base video of the avatar. For video thumbnail retrieval, please refer to our FAQ: How to get video thumbnails? - **people_img** (string) - The matting image of the avatar. When the field is empty, it means that the image cannot be matting. - **lang** (array of strings) - Supported languages for the avatar. - **width** (integer) - Width of the avatar. - **height** (integer) - Height of the avatar. - **user_photo_twin_id** (string) - User photo twin ID associated with the avatar. - **user_photo_twin_image_id** (string) - User photo twin image ID associated with the avatar. - **user_video_twin_id** (string) - User video twin ID for querying this API. - **video_cover** (string) - The video thumbnail obtained from `base_video`. - **wl_model** (string) - Legacy field. - **decode_img** (string) - Legacy field. - **decode_img_icon** (string) - Legacy field. #### Response Example ```json { "code": 0, "data": [ { "type": "custom", "_id": "660bc9da690879c4b5b20e82", "createdAt": "2024-04-01T10:00:00Z", "isExclusive": true, "wl_model": "legacy_model", "background_img": "http://example.com/bg.png", "background_color": "#FFFFFF", "base_video": "http://example.com/base.mp4", "people_img": "http://example.com/people.png", "lang": ["en", "es"], "width": 1920, "height": 1080, "user_photo_twin_id": "user_photo_id_123", "user_photo_twin_image_id": "user_photo_image_id_456", "user_video_twin_id": "660bc9da690879c4b5b20e82", "video_cover": "http://example.com/cover.jpg", "decode_img": "legacy_decode.png", "decode_img_icon": "legacy_icon.png" } ] } ``` ``` -------------------------------- ### POST /api/v1/userText2image/start Source: https://api.a2e.ai/start-text-to-image-13401494e0 Initiates the process of generating an image from a given text prompt. This endpoint accepts various parameters to control the image generation, including name, prompt, style (req_key), width, and height. ```APIDOC ## POST /api/v1/userText2image/start ### Description Starts the Text-to-Image generation process. This endpoint takes a text prompt and other parameters to create a unique image. ### Method POST ### Endpoint /api/v1/userText2image/start ### Parameters #### Path Parameters None #### Query Parameters None #### Request Body - **name** (string) - Required - The name associated with the request. - **prompt** (string) - Required - The text prompt for the image generation. - **req_key** (string) - Required - The style of the generated image. Enum: `high_aes_general_v21_L` (General Style), `high_aes` (Manga Style). - **width** (integer) - Required - The width of the generated image. - **height** (integer) - Required - The height of the generated image. ### Request Example ```json { "name": "Test Name", "prompt": "Generate an image of a sunset", "req_key": "high_aes_general_v21_L", "width": 1024, "height": 768 } ``` ### Response #### Success Response (200) - **code** (integer) - 0 is OK - **data** (object) - Contains the generated image details. - **trace_id** (string) - Unique identifier for the request trace. #### Response Example ```json { "code": 0, "data": { "name": "Test Name", "image_urls": [ "https://prod-tos.avatar2everyone.com/adam2eve/beta/reUpload/b2fb5131-c400-4a89-9ca4-61b9f0bccf59.image" ], "current_status": "completed", "failed_code": "", "failed_message": "", "_id": "6791ef3ccd837ce76eb01b75", "prompt": "Generate an image of a sunset", "req_key": "high_aes_general_v21_L", "width": 1024, "height": 768, "user_id": "665da3d7bcf6ab778bad0f6a", "coins": 20, "createdAt": "2025-01-23T07:26:52.420Z", "updatedAt": "2025-01-23T07:26:52.420Z" }, "trace_id": "78a3cae7-f1e9-49f2-954c-a844dc5cfdd3" } ``` ```