vod_separate_audio
Split a public audio or video URL into voice and background tracks (plus music and sfx for Drama/Narrate scenes) with MediaKit.
Returns a task_id; poll it with vod_get_task (operation ‘separate_audio’). Not retried automatically. Requires background execution (ark_job_submit).
| Requirement | Value |
|---|---|
| Registration | Requires BYTEPLUS_VOD_MEDIAKIT_API_KEY. |
| Execution | Background required |
| Required permission | vod:extract |
This site lists the full configured capability surface, not the tools enabled on your particular server. Use model discovery and job discovery to check your connection. Credentials are server configuration, never tool arguments.
Ask your connected AI client to use vod_separate_audio for the operation you want.
The client constructs the arguments and handles tool calls. Review its proposed
operation before approving anything billable. For a non-billable introduction,
start with discovery without generation.
Submit through ark_job_submit with tool_name and the complete target arguments, including its inner input object. Poll ark_job_get using the returned Ark job_id, respecting poll_after_ms. Inspect both terminal status and result.is_error; the original output is in result.structured_content. Do not call this tool in the foreground.
Match the input fields below and the full JSON Schema. See the worked examples for this capability and Background Execution for job/result handling.
An Ark job ID is not a provider task ID. Video and 3D tasks use gen_task_get, VOD tasks use vod_get_task, and avatars use omnihuman_get_task. Save accepted provider task IDs and resume polling instead of submitting a second generation.
Inputs
Section titled “Inputs”The MCP arguments object wraps these fields as {"input": {...}}.
| Field | Type | Required | Description and constraints |
|---|---|---|---|
audio_url |
string or null | No | Public HTTPS audio URL (mp3, m4a, wav). Set exactly one of audio_url or video_url.; Default: null |
output_format |
“aac”, “mp3”, “wav”, “m4a”, “flac” | No | Output audio format.; Default: “aac” |
scene |
“Audio”, “Music”, “Drama”, “Narrate” | No | Audio and Music give voice + background tracks; Drama and Narrate give voice + music + sfx tracks.; Default: “Audio” |
video_url |
string or null | No | Public HTTPS video URL (mp4, flv, ts, avi, mov, wmv, mkv). Set exactly one of audio_url or video_url.; Default: null |
Outputs
Section titled “Outputs”| Field | Type | Required | Description and constraints |
|---|---|---|---|
operation |
“enhance”, “transcode”, “separate_audio”, “add_subtitles”, “remove_subtitles” | No | Operation name; pass it to vod_get_task with task_id.; Default: “separate_audio” |
provider |
“byteplus-vod-mediakit” | No | Provider surface.; Default: “byteplus-vod-mediakit” |
provider_log_id |
string or null | No | Provider x-tt-logid, when returned.; Default: null |
recommended_poll_after_ms |
integer | Yes | Suggested delay before the first vod_get_task poll, in milliseconds. |
request_id |
string or null | No | Provider request ID, when returned.; Default: null |
status |
“accepted” | Yes | Always accepted; the task is asynchronous. |
task_id |
string | Yes | Task ID to poll with vod_get_task (operation ‘separate_audio’). |
Nested Types
Section titled “Nested Types”Field types named above refer to these shared definitions. Optional/null fields, enum choices and bounds are retained in the complete schemas below. Schema validation is followed by runtime capability and security checks.
VodSeparateAudioInput
| Field | Type | Required | Description and constraints |
|---|---|---|---|
audio_url |
string or null | No | Public HTTPS audio URL (mp3, m4a, wav). Set exactly one of audio_url or video_url.; Default: null |
output_format |
“aac”, “mp3”, “wav”, “m4a”, “flac” | No | Output audio format.; Default: “aac” |
scene |
“Audio”, “Music”, “Drama”, “Narrate” | No | Audio and Music give voice + background tracks; Drama and Narrate give voice + music + sfx tracks.; Default: “Audio” |
video_url |
string or null | No | Public HTTPS video URL (mp4, flv, ts, avi, mov, wmv, mkv). Set exactly one of audio_url or video_url.; Default: null |
Complete JSON Schemas
Section titled “Complete JSON Schemas”Input schema, including the MCP wrapper
{ "$defs": { "VodSeparateAudioInput": { "description": "Public source URL and separation options for the MediaKit separate-voice task.", "properties": { "audio_url": { "anyOf": [ { "format": "uri", "minLength": 1, "type": "string" }, { "type": "null" } ], "default": null, "description": "Public HTTPS audio URL (mp3, m4a, wav). Set exactly one of audio_url or video_url." }, "output_format": { "default": "aac", "description": "Output audio format.", "enum": [ "aac", "mp3", "wav", "m4a", "flac" ], "type": "string" }, "scene": { "default": "Audio", "description": "Audio and Music give voice + background tracks; Drama and Narrate give voice + music + sfx tracks.", "enum": [ "Audio", "Music", "Drama", "Narrate" ], "type": "string" }, "video_url": { "anyOf": [ { "format": "uri", "minLength": 1, "type": "string" }, { "type": "null" } ], "default": null, "description": "Public HTTPS video URL (mp4, flv, ts, avi, mov, wmv, mkv). Set exactly one of audio_url or video_url." } }, "type": "object" } }, "additionalProperties": false, "properties": { "input": { "$ref": "#/$defs/VodSeparateAudioInput" } }, "required": [ "input" ], "type": "object"}Output schema, including nested definitions
{ "description": "Accepted asynchronous voice and background audio separation submission.", "properties": { "operation": { "default": "separate_audio", "description": "Operation name; pass it to vod_get_task with task_id.", "enum": [ "enhance", "transcode", "separate_audio", "add_subtitles", "remove_subtitles" ], "title": "Operation", "type": "string" }, "provider": { "const": "byteplus-vod-mediakit", "default": "byteplus-vod-mediakit", "description": "Provider surface.", "title": "Provider", "type": "string" }, "provider_log_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Provider x-tt-logid, when returned.", "title": "Provider Log Id" }, "recommended_poll_after_ms": { "description": "Suggested delay before the first vod_get_task poll, in milliseconds.", "title": "Recommended Poll After Ms", "type": "integer" }, "request_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "Provider request ID, when returned.", "title": "Request Id" }, "status": { "const": "accepted", "description": "Always accepted; the task is asynchronous.", "title": "Status", "type": "string" }, "task_id": { "description": "Task ID to poll with vod_get_task (operation 'separate_audio').", "title": "Task Id", "type": "string" } }, "required": [ "status", "task_id", "recommended_poll_after_ms" ], "title": "VodSeparateAudioOutput", "type": "object"}Troubleshooting
Section titled “Troubleshooting”- Missing tool: check provider credentials and feature flags, then restart the connection.
- Invalid arguments: keep the correct wrapper and follow current model limits from discovery. A valid schema alone does not prove the chosen model supports the combination.
- A job completes with an error: inspect the original tool result, not only the outer job status. Never automatically resubmit potentially billable work.
- Local output writes from jobs require server-configured
OUTPUT_ROOTS; HTTP cannot write to a client’s local disk.
See configuration, background execution, and artifact delivery.