Get audio
get_audioRead one audio file by media ID. Returns its stable link, source, brand, MIME type, size, duration, description, and Library status.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"id": "<id>"
},
"name": "get_audio"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Media ID of the audio file, from list_audio or a generation output's id. | |
| llm_model | No | The model identifier you are running as, for example "claude-opus-4-8" or "gpt-5.2". Omit it or pass "unknown" if you are not certain; the tool runs the same either way. Recorded only for the server developer's analytics. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Media ID of the file. | |
| url | Yes | Stable link to the file. | |
| type | Yes | Media family: image, video, or audio. | |
| width | Yes | Width in pixels, or null when not recorded. | |
| height | Yes | Height in pixels, or null when not recorded. | |
| source | Yes | uploaded, scraped (collected from a brand source), or generated. | |
| file_size | Yes | File size in bytes. | |
| mime_type | Yes | MIME type of the file. | |
| created_at | Yes | Time the file was stored. | |
| in_library | Yes | Whether the file is in its Brand Library. | |
| description | Yes | Text description of the file, or null when there is none. | |
| duration_ms | Yes | Duration in milliseconds, or null when not recorded. | |
| workspace_id | Yes | Workspace ID, or null for a personal workspace that has no ID. | |
| generation_id | Yes | ID of the generation that produced the file, or null when none is recorded. | |
| brand_session_id | Yes | Brand session ID of the brand the file belongs to. |