io.github.AudialAI/audial-mcp

Official

Overview Schema Source Related Servers Discussions Admin

Segment audio

segment

Detects song sections, tempo, and bar grid from a full audio mix without stems, returning section phrases and a tempo map for structural analysis.

Instructions

Find song sections, tempo and bars (about half a minute).

Use for song structure. Send the mix: no stems needed, and it counts as one run. The result has the sections (with their phrases) and a tempo map. Beats and bars are not listed one by one: grid describes them -- where each constant-tempo piece starts, its BPM, and its bar and beat. Every beat time is start + k * 60 / bpm, and most tracks have one piece. The analysis_id it returns adds audio_features, tag_audio, get_lyrics or generate_samples to this analysis without another run. For tempo and key alone, analyze is quicker.

Input Schema

Name	Required	Description
`edm`	No	true: dance section names (INTRO, UP, CHORUS, DOWN, OUTRO); false: song section names (INTRO, VERSE, UP, CHORUS, OUTRO). Default: from the genre, else from the audio.
`genre`	No	Genre hint for the section names, e.g. 'Tech House', 'Pop' or 'Drum N Bass' (a name Audial does not know returns the list).
`features`	No	Optional, kept for older integrations: also compute these in the same call (mode, energy, loudness, danceability, tatum, tags, lyrics). The call then waits for them, minutes for tags and lyrics. Simpler: audio_features, tag_audio or get_lyrics afterwards with the analysis_id.
`file_path`	Yes	Full path to a local audio file (.wav, .mp3, .aif, .aiff, .flac, .m4a, .ogg, .aac). ~ is expanded.

Output Schema

Name	Required	Description	Default
`tool`	Yes
`files`	Yes
`summary`	Yes
`metadata`	Yes
`output_dir`	Yes
`execution_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.7.0Nov 7, 2026

removedInput schema / properties / analysis_type

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Analysis type accepted by Audial's segmentation.",
-  "title": "Analysis Type"
-}

removedInput schema / properties / components

Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Components to analyze, e.g. ['vocals', 'drums'].",
-  "title": "Components"
-}

addedInput schema / properties / edm

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "true: dance section names (INTRO, UP, CHORUS, DOWN, OUTRO); false: song section names (INTRO, VERSE, UP, CHORUS, OUTRO). Default: from the genre, else from the audio.",
+  "title": "Edm"
+}

changedInput schema / properties / features / description

Previous value: -"Features to compute per segment."New value: +"Optional, kept for older integrations: also compute these in the same call (mode, energy, loudness, danceability, tatum, tags, lyrics). The call then waits for them, minutes for tags and lyrics. Simpler: audio_features, tag_audio or get_lyrics afterwards with the analysis_id."

changedInput schema / properties / genre / description

Previous value: -"Genre hint that improves section detection."New value: +"Genre hint for the section names, e.g. 'Tech House', 'Pop' or 'Drum N Bass' (a name Audial does not know returns the list)."

First observedv0.1.1Sep 29, 2026

TDQS

A4.1/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, consistent with a job that creates an analysis and consumes a run. The description adds real context beyond that: runtime, that it counts as one run, and how the returned `grid` encodes beats/bars. However, it does not explain the cost model or what a failed or partial run looks like, so the behavioral disclosure is useful but not comprehensive.

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-loads the capability and runtime, then moves to usage, output shape and chaining alternatives, so an agent can stop reading early. Some material, such as the beat-time formula and the legacy `features` note, is dense but earns its place by preventing misinterpretation.

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?

An output schema exists, and the description still clarifies how to interpret `grid` rather than enumerating beats, which is the one thing a schema can't convey. The analysis_id reuse path is covered, so nothing critical for correct invocation appears to be missing.

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 coverage is 100%, with edm, genre and features already documented in the schema itself, so the baseline is 3. The description adds only an input hint (send the mix, no stems) and a run-cost note, which don't map to specific parameters beyond file_path.

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?

Opens with a concrete verb and resource set: find song sections, tempo and bars, plus explicit runtime (~half a minute). It also distinguishes itself from the sibling analyze ("For tempo and key alone, analyze is quicker"), so an agent can choose without comparing schemas.

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 explicit when-to-use (song structure) and when-not-to (tempo/key alone → analyze), plus an input rule (send the mix, no stems) and a chaining path for audio_features, tag_audio, get_lyrics and generate_samples via analysis_id instead of another run.

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