> ## Documentation Index > Fetch the complete documentation index at: https://docs.powertokens.ai/llms.txt > Use this file to discover all available pages before exploring further. # Vidu Timing-to-Audio > Generate controllable sound effect clips using the Vidu model based on timeline. Creators can freely control the timing of multiple sound events within the audio through a timeline. (BGM not supported) After submission, query status via `GET /vidu/ent/v2/tasks/{task_id}/creations`. ## OpenAPI ````yaml api-reference/en/zmodelAudio/vidu/vidu-timing-to-audio.json POST /vidu/ent/v2/timing2audio openapi: 3.0.1 info: title: Vidu Timing-to-Audio version: 1.0.0 servers: - url: https://api.powertokens.ai security: [] paths: /vidu/ent/v2/timing2audio: post: summary: Vidu Timing-to-Audio description: >- Generate controllable sound effect clips using the Vidu model based on timeline. Creators can freely control the timing of multiple sound events within the audio through a timeline. (BGM not supported) After submission, query status via `GET /vidu/ent/v2/tasks/{task_id}/creations`. operationId: viduTimingToAudioEn requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/TimingToAudioRequest' examples: basic_timing_audio: summary: Basic timing audio value: model: audio1.0 duration: 10 timing_prompts: - from: 0 to: 3 prompt: Rain sound - from: 2 to: 5 prompt: Thunder - from: 6 to: 9 prompt: Birdsong seed: 42 overlapping_events: summary: Overlapping sound events value: model: audio1.0 duration: 8 timing_prompts: - from: 0 to: 8 prompt: Ambient background sound - from: 1 to: 3 prompt: Footsteps - from: 4 to: 6 prompt: Door opening sound - from: 7 to: 8 prompt: Door closing sound precise_control: summary: Precise timing control value: model: audio1.0 duration: 5 timing_prompts: - from: 0 to: 0.5 prompt: Phone unlock sound - from: 1 to: 1.5 prompt: Keyboard typing sound - from: 2.5 to: 3 prompt: Message notification sound - from: 4 to: 4.5 prompt: Notification ringtone seed: 123456 responses: '200': description: Submission successful, returns an audio task object. content: application/json: schema: $ref: '#/components/schemas/TimingToAudioResponse' examples: success: value: task_id: your_task_id_here state: created model: audio1.0 duration: 10 timing_prompts: - from: 0 to: 3 prompt: Birds chirping in the morning - from: 3 to: 6 prompt: A distant train passing by - from: 5 to: 9.5 prompt: Waves gently lapping the beach seed: 0 credits: 10 created_at: '2025-01-01T10:00:00.000Z' security: - BearerAuth: [] components: schemas: TimingToAudioRequest: type: object required: - model - timing_prompts properties: model: type: string enum: - audio1.0 description: >- Audio generation model name. - **audio1.0**: Supports generating controllable sound effects based on timeline duration: type: number format: float default: 10 minimum: 2 maximum: 10 description: |- Audio duration in seconds. - Default: 10 seconds - Range: 2-10 seconds timing_prompts: type: array minItems: 1 items: $ref: '#/components/schemas/TimingPrompt' description: >- Timeline-based sound event prompts list. Each item defines a sound event with from and to timestamps and a prompt description. Notes: - Max 1500 characters per event prompt - Events can overlap - from and to must be within [0, duration] range seed: type: integer description: |- Random seed. - If not provided or set to 0, a random value will be used - Fixed value ensures reproducibility callback_url: type: string description: >- Callback When creating a task, you need to actively set the callback_url with a POST request. When the video generation task changes its status, Vidu will send a callback request to this URL, containing the latest status of the task. The structure of the callback request content will be the same as the return body of the GET Generation API.The "status" in the callback response includes the following states:- processing: Task is being processed.- success: Task is completed (if sending fails, it will retry the callback three times).- failed: Task failed (if sending fails, it will retry the callback three times).Vidu uses a callback signature algorithm for verification, check out the details here: Callback Signature TimingToAudioResponse: type: object properties: task_id: type: string description: Vidu generated Task ID state: type: string enum: - created - queueing - processing - success - failed description: |- Task state: - created: Task created successfully - queueing: Task in queue - processing: Task is being processed - success: Generation successful - failed: Task failed model: type: string description: Model parameter used duration: type: integer description: Audio duration timing_prompts: type: array items: $ref: '#/components/schemas/TimingPrompt' description: List of configured sound events seed: type: integer description: Random seed used credits: type: integer description: The credits used for this call created_at: type: string description: Task creation timestamp (ISO8601 format) TimingPrompt: type: object required: - from - to - prompt properties: from: type: number format: float minimum: 0 description: |- Sound event start time in seconds. Must be within [0, duration] range. to: type: number format: float description: |- Sound event end time in seconds. Must be within [0, duration] range and greater than from. prompt: type: string maxLength: 1500 description: >- Text description of the sound event, with a maximum length of 1500 characters. securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: 'Pass `Authorization: Bearer ` in the request header.' ````