Magic Hour

lip_sync_create_video

What this API does

Create the same Lip Sync you can make in the browser, but programmatically, so you can automate it, run it at scale, or connect it to your own app or workflow.

Good for

Automation and batch processing
Adding lip sync into apps, pipelines, or tools

How it works (3 steps)

Upload your inputs (video, image, or audio) with Generate Upload URLs and copy the file_path.
Send a request to create a lip sync job with the basic fields.
Check the job status until it's complete, then download the result from downloads.

Key options

Inputs: usually a file, sometimes a YouTube link, depending on project type
Resolution: free users are limited to 576px; higher plans unlock HD and larger sizes
Extra fields: e.g. face_swap_mode, start_seconds/end_seconds, or a text prompt

Cost
Credits are only charged for the frames that actually render. You'll see an estimate when the job is queued, and the final total after it's done.

For detailed examples, see the product page.

MCP guidance:

This starts an async video generation job and returns id plus credits_charged immediately. If the user wants the finished result, call the wait_for_video_project helper with the returned id, or poll the matching GET /v1/video-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 video a custom name for easy identification.	Lip Sync - dateTime
`style`	No	Attributes used to dictate the style of the output
`assets`	Yes	Provide the assets for lip-sync. For video, The `video_source` field determines whether `video_file_path` or `youtube_url` field is used
`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."
`end_seconds`	Yes	End time of your clip (seconds). Must be greater than start_seconds.
`max_fps_limit`	No	Defines the maximum FPS (frames per second) for the output video. If the input video's FPS is lower than this limit, the output video will retain the input FPS. This is useful for reducing unnecessary frame usage in scenarios where high FPS is not required.
`start_seconds`	Yes	Start time of your clip (seconds). Must be ≥ 0.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`id`	Yes	Unique ID of the video. Use it with the [Get video Project API](https://docs.magichour.ai/api-reference/video-projects/get-video-details) to fetch status and downloads.
`credits_charged`	Yes	The amount of credits deducted from your account to generate the video. If the status is not 'complete', this value is an estimate and may be adjusted upon completion based on the actual FPS of the output video. If video generation fails, 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

A4.5/5.0

Behavior5/5

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

With no annotations present, the description carries the full burden and does so well: it discloses async behavior (returns id and credits_charged immediately), the terminal statuses (complete/error/canceled), that downloads carry direct URLs, that credits are charged only for rendered frames with an estimate at queue time, resolution limits by plan tier, and generation_mode tier availability.

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

Conciseness3/5

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

Headers and the 3-step flow are well front-loaded, but the piece is long and mixes marketing copy ('the same Lip Sync you can make in the browser') and cost details that duplicate the schema's generation_mode pricing. The genuinely load-bearing MCP guidance is buried at the bottom.

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 the tool starts an async job, an output schema exists, and the schema is fully described, the description supplies everything else an agent needs: the immediate return shape, the waiting/polling path, the completed-project downloads, and how to obtain valid file_path values.

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%, so the schema already documents all seven parameters, making 3 the baseline. The 'Key options' section adds some framing (inputs, resolution, start_seconds/end_seconds) but it also lists a field like 'face_swap_mode' that does not exist on this schema, adding noise rather than the missing detail the schema could not supply.

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?

The description opens with a specific verb+resource ('Create the same Lip Sync... programmatically') and scopes it as an automated/batch/embedded capability. It is clearly distinguishable from siblings like face_swap_create_video or ai_video_editor_create_video because the resource (lip sync) and its async nature are explicit.

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?

It gives concrete when-to-use guidance ('Automation and batch processing', 'Adding lip sync into apps, pipelines, or tools') and an explicit routing rule: call wait_for_video_project or poll GET /v1/video-projects/{id} when the finished result is wanted. It also states when to prefer the presigned upload flow over hotlinked URLs.

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.