Skip to main content
Glama
Sign In

switch

by ai.switchapp
OverviewDiscussionsAdmin

Video to Music

video_to_music

Write a soundtrack for a video from the video itself, with ElevenLabs Video to Music: it watches the cuts, pace and mood and scores them. Use it when the customer asks for music made for their video ("write a soundtrack for this", "score my clip"). When they bring their own song (for example from Suno), use that song instead and do not call this. Pass the video in video_url (the file id or name from this chat, or an https link), or video_id for a video made in Switch (its job id from list_my_videos; up to 10 videos in video_urls, all together up to 200 MB and 10 minutes). Optional: description (the music in words, up to 4100 characters), tags (up to 10 styles, like "cinematic", "lofi"), add_sound_effects (sound effect cues from the picture), use_video_sound_as_reference (its genre, tempo, instruments, mood and arc from the video's own sound), separate_tracks (the music and the effects as two files), video_seconds (the video's length, for the hold). HOUSE RULE: only make music when the customer asked for music. Billed like generate_music, per 10 seconds of the track (a token quote applies). Returns audio_url, duration_seconds and generation_id, and effects_track with separate_tracks. It does not put the music on the video: add_sound_to_video or the Editor does that.

Input Schema

NameRequiredDescriptionDefault
tagsNoOptional styles, up to 10.
model_idNoOptional ElevenLabs model id; leave out for their default.
video_idNoA video made in Switch, by its job id (list_my_videos, get_video_status); its stored file is used.
video_urlNoThe video in this chat by its file id or name, or an https link.
video_urlsNoOptional, several videos scored as one, in order (up to 10).
descriptionNoOptional. The music in plain words: genre, mood, instruments, how it builds.
video_secondsNoOptional. The video's length in seconds, so the right amount is held before it starts.
separate_tracksNoOptional. true returns the music and the sound effects as two files.
add_sound_effectsNoOptional. true adds sound effect cues taken from the picture.
use_video_sound_as_referenceNoOptional. true takes the genre, tempo, instruments, mood and arc from the video's own sound.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / video_id
      Added value: +{
+  "description": "A video made in Switch, by its job id (list_my_videos, get_video_status); its stored file is used.",
+  "type": "string"
+}
  2. Added

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description doesn't need to restate the safety profile. It does add genuinely useful behavior the annotations lack: billing model ('per 10 seconds of the track, a token quote applies') and hard limits (10 videos, 200 MB, 10 minutes). It stops short of return-format edge cases and failure behavior, so it's good but not rich.

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, then routing, inputs, options, billing and outputs in a sensible order; nothing is filler. It is dense with parenthetical asides and the final sentence on add_sound_to_video is long, which costs a point on readability, but every clause carries information.

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 10-param generation tool with no output schema, the description covers when to call, all option semantics, size/duration limits, billing, and what is returned (audio_url, duration_seconds, generation_id, effects_track). It also closes the workflow gap by naming the follow-up tool that actually attaches music to video.

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 100%, so baseline is 3; the description earns above baseline by adding constraints not present in the schema, notably the 200 MB / 10 minute combined limits for video_urls and the 4100-character description cap. It also links video_id to list_my_videos and adds the conversational sourcing of video_url, which helps an agent populate otherwise opaque file references.

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+resource ('Write a soundtrack for a video from the video itself') and names the underlying service (ElevenLabs Video to Music). It explains the mechanism (watches cuts, pace, mood) which clearly separates it from generate_music and plan_music siblings.

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?

Explicit when-to-use with customer phrasings ('write a soundtrack for this', 'score my clip'), explicit when-not (customer brings their own Suno song), and a HOUSE RULE gate ('only make music when the customer asked for music'). It also names add_sound_to_video for the adjacent step of putting music on the video.

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

All switch toolsInspect
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