VidGuy

Character Swap: create

create_character_swap

Destructive

Swap a character image onto a driving video, optionally restoring selected source-video ranges in the final result. ASYNC — returns a projectId; poll get_job. SPENDS CREDITS (Standard: min 25, about 1 per swapped second, ×2 for 1080p. Pro: 5.5 credits per swapped second, 8.25 at 1080p, each section billed at least 3 s, min 25 / 50. +5 voice change). Needs a character-image r2Key (from swap_import_character for an image already on VidGuy, or swap_upload for raw bytes) and a driving-video r2Key from swap_upload. A driving-video r2Key is reusable: upload the source once, then call this repeatedly with different characters to batch one cut across many avatars. get_video on a finished swap returns its exact settings (ranges, keys) to replay.

Input Schema

Name	Required	Description
`name`	No
`engine`	No	Visual engine. Both take any length up to 2 minutes. "standard" (default): about 1 credit per swapped second. "pro": closest likeness and movement, lips follow the speech; 5.5 credits per swapped second (8.25 at 1080p), each swapped section billed at least 3 s.
`prompt`	No
`saveAudio`	No	Keep the driving video's original audio in the result (default true). Set false to drop it. Ignored when voiceChangeVoiceId is set — voice change always keeps audio.
`resolution`	No
`sceneMatch`	No
`characterR2Key`	Yes	character-image r2Key from swap_upload
`characterFileName`	Yes
`drivingVideoR2Key`	Yes	driving-video r2Key from swap_upload
`voiceChangeVoiceId`	No	If set, enables voice change with this ElevenLabs voice id (+5 credits)
`drivingVideoFileName`	Yes
`drivingDurationSeconds`	Yes	Driving video length (drives cost)
`keepOriginalVisualRanges`	No	Up to 20 ranges to keep exactly as filmed, e.g. screen recordings. Times are milliseconds and each range must be at least 250 ms. The swap applies everywhere else; audio processing is unchanged.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 26, 2026

changedInput schema / properties / engine / description

Previous value: -"Visual engine. Both take any length up to 2 minutes. \"standard\" (default): about 1 credit per swapped second. \"pro\": closest likeness and movement, lips follow the speech; 4.7 credits per swapped second (7.05 at 1080p), each swapped section billed at least 3 s."New value: +"Visual engine. Both take any length up to 2 minutes. \"standard\" (default): about 1 credit per swapped second. \"pro\": closest likeness and movement, lips follow the speech; 5.5 credits per swapped second (8.25 at 1080p), each swapped section billed at least 3 s."

Changed1 schema field changedOct 26, 2026

changedInput schema / properties / engine / description

Previous value: -"Visual engine. \"standard\" (default): any length up to 2 minutes. \"pro\": higher movement accuracy with lipsync, +2 credits; every swapped section (video minus keep-original ranges) must be 14 s or shorter or the request is rejected — add keepOriginalVisualRanges to split longer footage."New value: +"Visual engine. Both take any length up to 2 minutes. \"standard\" (default): about 1 credit per swapped second. \"pro\": closest likeness and movement, lips follow the speech; 4.7 credits per swapped second (7.05 at 1080p), each swapped section billed at least 3 s."

Changed1 schema field changedSep 15, 2026

addedInput schema / properties / engine

Added value: +{
+  "description": "Visual engine. \"standard\" (default): any length up to 2 minutes. \"pro\": higher movement accuracy with lipsync, +2 credits; every swapped section (video minus keep-original ranges) must be 14 s or shorter or the request is rejected — add keepOriginalVisualRanges to split longer footage.",
+  "enum": [
+    "standard",
+    "pro"
+  ],
+  "type": "string"
+}

First observedSep 14, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already flag a destructive, non-idempotent, open-world write, and the description adds substantial context beyond that: ASYNC execution returning a projectId, explicit credit costs per engine and resolution with minimums, and the +5 voice-change surcharge. The reusable-driving-key batching note is a genuinely useful behavioral trait not derivable from any structured field.

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 the action and the ASYNC/credit warnings before the prerequisite detail, and each sentence carries distinct information. The dense parenthetical pricing stacks are justified but make it heavier than necessary.

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?

For a 13-parameter, credit-spending async mutation with no output schema, the description covers what an agent most needs: async contract, cost model, input provenance, batching strategy, and how to inspect or replay a result. Nothing critical to a correct first call is missing.

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?

At 54% schema coverage the description compensates well for the cost-bearing parameters: engine pricing tiers, 1080p multipliers, per-section 3s minimums, and the source of each r2Key. It leaves name, prompt, sceneMatch, and saveAudio's actual effect unexplained (saveAudio is only covered in the schema), so the compensation is strong but not complete.

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: 'Swap a character image onto a driving video,' plus the optional range-preservation behavior. It is clearly distinguishable from siblings like swap_upload and swap_import_character, which the description explicitly relegates to input-preparation roles.

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?

Gives the full call path: get the character r2Key from swap_import_character (existing image) or swap_upload (raw bytes), and the driving-video r2Key from swap_upload. It also names the follow-up tool (poll get_job) and the replay path (get_video), so the agent knows both prerequisites and next steps.

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

All VidGuy 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?