---
title: "Query Music Generation Detail"
method: GET
path: "/api/generate/detail/music"
tags: ["Music Generation"]
---

# Query Music Generation Detail

`GET /api/generate/detail/music`

Retrieve detailed results and status of a music generation task

## Query parameters

- `task_id` string, required

## Response `200`

Task detail retrieved successfully

- DetailResponse
  - `code` integer, required — HTTP status code
  - `data` object, required
    - `task_id` string, required — Unique task identifier
    - `status` 'not_started' | 'running' | 'finished' | 'failed', required — Current status of the task. - `not_started`: Task is queued but not yet processing - `running`: Task is currently being processed - `finished`: Task completed successfully - `failed`: Task failed due to an error
    - `credits_amount` number, required — Credits charged for the task. This field is returned at the task level and is not repeated inside `files`.
    - `files` AudioFile[], required — Array of generated files. The response fields vary depending on which model created the task. See [Response Fields (files data)](#response-fields-files-data) for details. Empty array when task is not finished or has failed.
      - `audio_id` string — Unique identifier for this audio file
      - `audio_url` string, uri — Direct URL to download the generated audio file
      - `image_url` string, uri — Direct URL to the cover image for this audio file. Present only for models that return a cover image.
      - `title` string — Title of the generated track
      - `tags` string — Style tags associated with the generated track
      - `duration` number — Duration of the audio file in seconds. Some models may return `0` when duration metadata is not available.
      - `prompt` string — Original prompt used for generation when available.
      - `text` string — Lyrics or text content returned by text-oriented music endpoints.
      - `timestampe_lyrics` string — Lyrics with timestamps.
      - `style` string — Style text returned by music style enhancement endpoints.
      - `wav_url` string, uri — Converted WAV file URL.
      - `separate_vocals` string — JSON string containing separated vocal and instrumental URLs.
      - `vocal_removal` string — JSON string containing separated stem URLs.
      - `stem_split` string — JSON string containing full stem separation URLs.
      - `generate_cover` string — JSON string containing generated cover image objects.
      - `persona_id` string — Generated persona identifier.
      - `video_url` string, uri — Generated video URL.
    - `created_time` string, date-time, required — ISO 8601 timestamp when the task was created
    - `error_message` string, nullable — Error message if the task failed. `null` when task is successful or still processing.

---

[API](https://skmtc.net/poyo/apis/poyo-ai-hunyuan-3d-v3-1-api.md) · [All operations](https://skmtc.net/poyo/apis/poyo-ai-hunyuan-3d-v3-1-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/poyo/poyo-ai-hunyuan-3d-v3-1-api/revisions/4b46904b78eb/schema)