> ## Documentation Index > Fetch the complete documentation index at: https://docs.aihubmax.com/llms.txt > Use this file to discover all available pages before exploring further. # OmniHuman 1.5 Digital Human Video Generation > - OmniHuman 1.5 audio-driven digital human video generation model - Input a portrait image + audio to generate a synchronized video of the character speaking/singing/performing - Supports turbo mode - Asynchronous processing mode; use the returned task ID to [query the task status](/pages/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours; please save them promptly ## OpenAPI ````yaml openapi/en/omnihuman-1.5.json POST /v1/videos/generations openapi: 3.1.0 info: title: OmniHuman 1.5 version: '1.0' servers: - url: https://api.aihubmax.com security: - BearerAuth: [] paths: /v1/videos/generations: post: tags: - Video > Audio-Visual Sync summary: OmniHuman 1.5 description: > - OmniHuman 1.5 audio-driven digital human video generation model - Input a portrait image + audio to generate a synchronized video of the character speaking/singing/performing - Supports turbo mode - Asynchronous processing mode; use the returned task ID to [query the task status](/pages/en/api-manual/task-management/get-task-detail) - Generated video links are valid for 24 hours; please save them promptly operationId: omnihuman-1.5 requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/OmniHumanGenRequest' examples: 基础数字人视频: summary: Basic digital human video value: model: omnihuman-1.5 image_url: https://example.com/portrait.jpg audio_url: https://example.com/speech.mp3 带文本引导_加速模式: summary: With text guidance + turbo mode value: model: omnihuman-1.5 image_url: https://example.com/portrait.jpg audio_url: https://example.com/speech.mp3 prompt: The person speaks calmly to the camera turbo_mode: true 指定分辨率_随机种子: summary: Specified resolution + random seed value: model: omnihuman-1.5 image_url: https://example.com/portrait.jpg audio_url: https://example.com/narration.wav prompt: A woman smiles while talking advanced: resolution: 720p seed: 42 responses: '200': $ref: '#/components/responses/TaskCreated' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '402': $ref: '#/components/responses/PaymentRequired' '422': $ref: '#/components/responses/UnprocessableEntity' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' '503': $ref: '#/components/responses/ServiceUnavailable' components: schemas: OmniHumanGenRequest: type: object required: - model - image_url - audio_url properties: model: description: '`omnihuman-1.5`: Audio-driven digital human video' examples: - omnihuman-1.5 type: string default: omnihuman-1.5 image_url: description: | Public URL of the portrait image **Notes:** - Formats: JPG / PNG / WebP / GIF / AVIF - File size up to 5MB - Must be a publicly accessible URL - The image must contain a human face type: string example: https://example.com/portrait.jpg audio_url: description: | Public URL of the audio file **Notes:** - Formats: MP3 / WAV / OGG / M4A / AAC - Must be a publicly accessible URL - Audio duration determines output video duration and billing - Duration limit: up to 30 seconds (up to 60 seconds in 720p mode) type: string example: https://example.com/speech.mp3 prompt: anyOf: - type: string - type: 'null' default: null description: > Text guidance to control character behavior and actions **Notes:** - Supports Chinese, English, Japanese, Korean, Spanish, and Indonesian - Describing dynamic actions works better; avoid describing static attributes already present in the image example: The person speaks calmly to the camera turbo_mode: anyOf: - type: boolean - type: 'null' default: null description: |- Turbo mode **Notes:** - Enables faster generation with slight quality loss - Suitable for quick iteration and previewing > Do not pass this parameter unless necessary. x-advanced: true example: true advanced: anyOf: - additionalProperties: false description: OmniHuman 1.5 advanced options. properties: resolution: anyOf: - type: string - type: 'null' default: null description: Output video resolution (advanced optional parameter) example: 1080p seed: anyOf: - type: integer - type: 'null' default: null description: >- Random seed; set a fixed value to reproduce generation results example: 42 type: object - type: 'null' default: null description: |- Advanced options for additional control > Do not pass this parameter unless necessary. x-advanced: true TaskResponse: type: object properties: created: type: integer description: Task creation timestamp example: 1757165031 id: type: string description: Task ID example: task-unified-1757165031-uyujaw3d model: type: string description: Actual model name used object: type: string description: Specific task type enum: - video.generation.task progress: type: integer description: Task progress percentage (0-100) minimum: 0 maximum: 100 example: 0 status: type: string description: Task status enum: - pending - processing - completed - failed example: pending task_info: type: object description: Asynchronous task information properties: can_cancel: type: boolean description: Whether the task can be canceled example: true estimated_time: type: integer description: Estimated completion time (seconds) example: 45 type: type: string description: Task output type enum: - video example: video ErrorResponse400: type: object properties: error: type: object properties: message: type: string example: Invalid request format type: type: string example: invalid_request_error ErrorResponse401: type: object properties: error: type: object properties: message: type: string example: Invalid API Key type: type: string example: authentication_error ErrorResponse402: type: object properties: error: type: object properties: message: type: string example: Insufficient account balance type: type: string example: insufficient_quota ErrorResponse422: type: object properties: error: type: object properties: message: type: string example: Parameter validation failed type: type: string example: validation_error ErrorResponse429: type: object properties: error: type: object properties: message: type: string example: Rate limit exceeded type: type: string example: rate_limit_error ErrorResponse500: type: object properties: error: type: object properties: message: type: string example: Internal server error type: type: string example: server_error ErrorResponse503: type: object properties: error: type: object properties: message: type: string example: Service temporarily unavailable, please try again later type: type: string example: service_unavailable responses: TaskCreated: description: Task created successfully content: application/json: schema: $ref: '#/components/schemas/TaskResponse' BadRequest: description: Invalid request format content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Unauthorized: description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse401' PaymentRequired: description: Insufficient balance content: application/json: schema: $ref: '#/components/schemas/ErrorResponse402' UnprocessableEntity: description: Parameter validation failed content: application/json: schema: $ref: '#/components/schemas/ErrorResponse422' TooManyRequests: description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/ErrorResponse429' InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse500' ServiceUnavailable: description: Service temporarily unavailable content: application/json: schema: $ref: '#/components/schemas/ErrorResponse503' securitySchemes: BearerAuth: type: http scheme: bearer description: | ## All endpoints require Bearer Token authentication ## Add the following to your request headers: `Authorization: Bearer YOUR_API_KEY` ````