Fotor

Submit Audio Track Task

submit_audio_track_task

Destructive

Starts one Fotor audio track generation task. Creates a new track from reference audio; use submit_audio_separation_task to extract existing vocals and accompaniment. May consume existing Fotor credits. Returns a task ID without waiting for completion; use get_task to check its status once. This tool does not poll for completion. Repeating the request may create another task and consume additional credits. Do not automatically retry when the submission outcome is uncertain. This tool does not purchase credits or initiate a checkout flow.

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": {
      "audio_url": "<audio_url>",
      "generate_type": "<generate_type>",
      "prompt": "<prompt>"
    },
    "name": "submit_audio_track_task"
  }
}

Input Schema

Name	Required	Description
`lyrics`	No	Lyrics for generated vocals.
`prompt`	Yes	Describe the desired track style and sound.
`audio_url`	Yes	Accessible HTTPS reference audio URL.
`vocal_gender`	No	Singing voice gender; only valid for generate_type=Vocals.
`generate_type`	Yes	Track to generate: Vocals = singing voice; Instrumental = music without vocals; Drums = drum kit; Bass = bass part; Guitar = guitar; Keyboard = keyboard instruments; Percussion = percussion; Strings = string section; Synth = synthesizer; FX = sound effects; Brass = brass section; Woodwinds = woodwind section.
`generate_end_ms`	No	Reference segment end in integer milliseconds.
`generate_start_ms`	No	Reference segment start in integer milliseconds.

Output Schema

Name	Required	Description	Default
`error`	No	Stable failure code; null when no failure is reported.
`status`	Yes	Observed task state. processing does not distinguish queued or running; unknown is an unrecognized upstream state.
`task_id`	Yes	Fotor task ID for get_task.
`model_id`	Yes	Model ID used for this task.
`task_type`	Yes	Audio operation performed.
`media_type`	No	Generated media category.	audio
`result_url`	No	Completed output URL; availability is not guaranteed permanently. Audio output may be MP3 or ZIP.
`is_terminal`	Yes	Whether the task has completed, failed, timed out or been cancelled.
`result_format`	No	Completed file format: mp3 audio or zip archive; null until completed.
`failure_reason`	No	Safe failure summary; may be generic rather than the upstream root cause.
`credits_increment`	No	Reported task credit cost; not an additional charge on each query. Null if unavailable.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 29, 2026

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing credit consumption ('May consume existing Fotor credits'), duplicate-task risk on repeat calls, the no-retry-on-uncertain-outcome guidance, and that the tool does not block or poll. These are exactly the operational facts annotations cannot convey. Slightly short of 5 because 'check its status once' is stated without explaining the rate-limit or cost rationale behind that constraint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and alternative in the first two sentences, then behavior caveats. Mild redundancy: 'Returns a task ID without waiting for completion' and 'This tool does not poll for completion' say the same thing twice, and the credits warning appears twice in different forms.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists, the description needn't explain return values, and it covers the remaining decision-critical gaps: credit cost, non-idempotency, the follow-up status check, and retry policy. An agent has everything needed to call this correctly and safely without guessing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the descriptions cover every parameter, including enum meanings and the conditional rule that vocal_gender is only valid for generate_type=Vocals. The tool description adds no parameter guidance of its own, so this sits at the baseline for a fully documented schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Starts one Fotor audio track generation task. Creates a new track from reference audio') and explicitly contrasts with the sibling it is not: 'use submit_audio_separation_task to extract existing vocals and accompaniment'. An agent can route between the two submission tools without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names the alternative tool and the condition that selects it, then specifies the follow-up path ('use get_task to check its status once') and the exclusion ('does not purchase credits or initiate a checkout flow'). This is explicit when-to-use, when-to-use-something-else, and what-this-is-not.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Fotor tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?