Skip to main content
Glama
AIWerk

@aiwerk/mcp-server-elevenlabs

by AIWerk
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

generate

Compose music from prompts, lyrics, or composition plans, returning audio bytes; set output_path to save the file. Uses ElevenLabs credits.

Instructions

Compose Music Spends ElevenLabs credits. Returns audio/* bytes; pass output_path to save them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seedNo
promptNo
model_idNo
finetune_idNo
lyrics_textNo
output_pathNoWhere to write the returned bytes. Relative paths resolve against ELEVENLABS_OUTPUT_DIR. Omit it to get the data inline as base64 (small files only).
music_promptNoComposition plan for the `music_v1` model. Using this field with any other model will result in an error.
output_formatNoOutput format of the generated audio. Formatted as codec_sample_rate_bitrate. Use "auto" (the default) to let the API pick the best format for the selected model: mp3_44100_128 for v1 models and mp3_48000_192 for v2 models.
sign_with_c2paNoWhether to sign the generated song with C2PA. Applicable only for mp3 files.
generation_modeNo
music_length_msNo
composition_planNo
finetune_strengthNoHow strongly the finetune influences the generation. Defaults to 1.0 (full strength). Lower values soften the influence of the finetune, leaving more room for prompt-level steering. Only meaningful when `finetune_id` is also provided.
force_instrumentalNoIf true, guarantees that the generated song will be instrumental. If false, the song may or may not be instrumental depending on the `prompt`. Can only be used with `prompt`.
use_phonetic_namesNoIf true, proper names in the prompt will be phonetically spelled in the lyrics for better pronunciation by the music model. The original names will be restored in word timestamps.
store_for_inpaintingNoWhether to store the generated song for inpainting.
respect_sections_durationsNoControls how strictly section durations in the `composition_plan` are enforced. Only used with `composition_plan` and only applies to `music_v1`; for `music_v2` and `music_v2_5` section durations are always enforced and this is ignored. When false for `music_v1`, the model may adjust individual sect

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior4/5

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

Annotations only declare it is a non-read-only, non-idempotent, open-world operation, so the description earns real credit by disclosing that it spends ElevenLabs credits and returns audio/* bytes. The credit-consumption cost is exactly the kind of trait annotations cannot convey.

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?

It is short and front-loads purpose, but the first sentence is an unpunctuated run-on ("Compose Music Spends ElevenLabs credits") that reads as two fragments fused together, hurting clarity more than length does.

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

Completeness2/5

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

For a 17-parameter generative tool with overlapping model_ids, music_prompt vs composition_plan, and multiple generation modes, two terse sentences leave major decisions unexplained. With no output schema and only 53% parameter coverage, the description should have carried far more of the complexity burden.

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?

With 17 parameters and 53% schema coverage, the schema already documents the heavier fields, and the description only echoes output_path behavior that the schema itself explains in more detail. It adds no model-selection or mode guidance beyond the structured data, so baseline 3 fits.

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

Purpose3/5

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

"Compose Music" gives a verb and resource, so the core purpose is legible despite the generic name "generate". However, it offers no differentiation from the many composition siblings (compose_detailed, compose_plan, stream_compose, sound_generation), so an agent cannot tell which composition tool to reach for from this text alone.

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

Usage Guidelines2/5

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

There is no statement of when to use this tool versus alternatives like compose_detailed or stream_compose. The only usage-shaped hint is the mechanical note about output_path, which is about output handling rather than tool selection.

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

Deploy Server

Other Tools