Magic Hour

by io.github.magichourhq

Overview Discussions Admin

ai_voice_cloner_create_audio

Clone a voice from an audio sample and generate speech.

Each character costs 0.1 credits.
The cost is rounded up to the nearest whole number

MCP guidance:

This starts an async audio generation job and returns id plus credits_charged immediately. If the user wants the finished result, call the wait_for_audio_project helper with the returned id, or poll the matching GET /v1/audio-projects/{id} endpoint until status is complete, error, or canceled. Completed projects include downloads with direct URLs. The custom wait helper also returns exact_download_urls separately from expiration metadata.
For *_file_path values, prefer an existing Magic Hour file path or a file_path returned by the upload-URL endpoint after the file bytes are uploaded. Direct public media URLs may work when they are stable, fetchable, and return raw file bytes, but hotlinked URLs can fail; when in doubt, use the presigned upload flow first and pass the returned file_path.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name`	No	Give your audio a custom name for easy identification.	Voice Cloner - dateTime
`style`	Yes
`assets`	Yes	Provide the assets for voice cloning.
`context`	No	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."

Output Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes	Unique ID of the audio. Use it with the [Get audio Project API](https://docs.magichour.ai/api-reference/audio-projects/get-audio-details) to fetch status and downloads.
`credits_charged`	Yes	The amount of credits deducted from your account to generate the audio. We charge credits right when the request is made. If an error occurred while generating the audio, credits will be refunded and this field will be updated to include the refund.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 11, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}

First observedSep 1, 2026

TDQS

A3.8/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that this is an async job returning id + credits_charged immediately, the cost model (0.1 credits/character, rounded up), terminal statuses (complete/error/canceled), and file-path failure modes with hotlinked URLs. It omits auth/permission requirements, which is the main remaining gap.

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?

Purpose is front-loaded, pricing follows, then operational guidance. Every sentence is load-bearing and there's no redundancy, though the guidance block is dense enough to slow scanning.

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

Completeness4/5

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

For a nested-parameter async generation tool with an output schema, the description covers the essential call flow, follow-up polling, return fields, and file-path pitfalls. Release/download retrieval is only partially described, but the output schema and wait helper cover the rest.

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

Parameters4/5

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

Schema coverage is 75%. The description adds real meaning beyond the schema: the cost-per-character rule ties to the length of style.prompt, and the MCP guidance explains the accepted forms of the assets.audio_file_path value plus presigned-upload fallback, which the schema only states abstractly.

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

Purpose4/5

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

States a specific verb+resource+action: 'Clone a voice from an audio sample and generate speech.' The 'from an audio sample' clause implicitly distinguishes it from the plain voice generator sibling, but it never names that sibling explicitly, so an agent must infer the boundary.

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

Usage Guidelines3/5

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

The MCP guidance gives useful workflow context (call wait_for_audio_project with the returned id, or poll the GET endpoint) and file-path prerequisites. However, it never states when to choose this over ai_voice_generator_create_audio, so the alternative-selection guidance is only implied.

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

All Magic Hour 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.