What can you do with this server?

Gemini Audio MCP is a professional-grade audio synthesis server leveraging Google's Gemini 2.5 and Lyria 3 AI models. It offers the following capabilities: * 🌿 Generate Soundscapes (generate_soundscape): Create immersive, vocal-free ambient audio (e.g., rainy forests, underwater environments) with optional image-guided mood, duration, and format settings. * 🎵 Generate Music (generate_music): Produce songs, loops, or musical segments using Lyria 3 Pro or Clip models, with control over BPM, key, intensity, and vocal presence. * 🗣️ Generate Voice (generate_voice): Synthesize expressive speech, narration, or character dialogue from text with custom tone/style directions. * 💥 Generate SFX (generate_sfx): Create isolated, short-duration sound effects and foley (e.g., laser blasts, footsteps). * 🔀 Transition Soundscapes (transition_soundscape): Crossfade seamlessly between two distinct audio environments. * ⚙️ Configure Server (configure): View or update defaults for format, sample rate, bitrate, channels, duration, and auto-cleanup intervals. * ▶️ Play Audio (play_audio): Play any local audio file using the system's default media player. * 🧹 Cleanup Assets (cleanup_assets): Delete old generated audio files to free disk space. * 🔍 Check Dependencies (check_dependencies): Verify required tools like FFmpeg are installed. Additional features include multimodal image input to guide audio mood, a seed parameter for deterministic/reproducible outputs, and automatic looping to extend or create infinite soundscapes.

Which integrations are available for this server?

Provides audio format conversion and transcoding capabilities, enabling export of generated soundscapes and music to WAV, MP3, OGG, and FLAC formats. Integrates with Google's Gemini 2.0 Multimodal Live API and Lyria 3 models (Pro and Clip) to generate dynamic environmental soundscapes, professional music, and high-fidelity audio content from text prompts.

Gemini Audio MCP

by jxoesneon

Overview Schema Source Related Servers Discussions Admin

Rust

Local

🎵 Gemini Audio MCP

Institutional Grade Gemini 2.5 Lyria 3

Gemini Audio MCP is a high-performance Model Context Protocol (MCP) server engineered for professional-grade audio synthesis. It leverages the Gemini 2.5 Multimodal Live API and Google DeepMind's Lyria 3 models to deliver high-fidelity environmental soundscapes, musical compositions, and expressive narration on-demand.

🛠 Prerequisites

Before deploying the server, ensure your environment meets the following technical requirements:

1. FFmpeg (Core Processing Engine)

Required for high-performance audio encoding, decoding, and transcoding.

macOS: brew install ffmpeg
Windows: winget install ffmpeg or download from ffmpeg.org.
Linux (Ubuntu/Debian): sudo apt update && sudo apt install ffmpeg

2. Rust Toolchain (Compilation)

Required to build the server from source.

Install via rustup.rs: curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

3. Node.js & NPM (Runtime)

Required if using the pre-compiled NPM package.

Version: node >= 18.0.0

Related MCP server: Talky Talky

🚀 Installation & Deployment

Global Installation (via NPX)

The fastest way to integrate the server into your MCP client (e.g., Claude Desktop).

{
  "mcpServers": {
    "gemini-audio": {
      "command": "npx",
      "args": ["-y", "gemini-audio-mcp"],
      "env": {
        "GEMINI_API_KEY": "YOUR_SECURE_API_KEY"
      }
    }
  }
}

Manual Build (Optimized)

For maximum performance, build the Rust binary locally:

Clone & Build:

git clone https://github.com/mcp-servers/gemini-audio-mcp.git
cd gemini-audio-mcp
cargo build --release

Locate Binary: The optimized binary will be in ./target/release/gemini-audio-mcp.

🔑 API Key Management

The server requires a valid Google AI Studio API key.

Obtain your key from Google AI Studio.
Security Best Practice: Never hardcode keys. Inject the key via the GEMINI_API_KEY environment variable.
Tier Note: Access to Lyria 3 (Pro/Clip) models typically requires a Paid Tier or specific preview access in Google AI Studio.

🎮 Tool Usage Guide

1. Environmental Generation (`generate_soundscape`)

Synthesizes immersive, vocal-free ambient textures.

{
  "name": "generate_soundscape",
  "arguments": {
    "prompt": "Deep underwater abyss, low-frequency whale songs, rhythmic air bubbles rising, muffled aquatic pressure.",
    "duration": 60,
    "quality": "high",
    "auto_play": true
  }
}

2. Professional Music (`generate_music`)

Generates structural compositions with optional vocal control.

{
  "name": "generate_music",
  "arguments": {
    "prompt": "Melancholic solo cello in a vast cathedral with 5-second decay reverb.",
    "bpm": 72,
    "song_key": "D minor",
    "intensity": 4
  }
}

3. Expressive Voice (`generate_voice`)

Narration and character dialogue using Gemini 2.5 Native Audio.

{
  "name": "generate_voice",
  "arguments": {
    "text": "The artifacts are stable, but the rift remains open.",
    "voice_direction": "Gravelly, urgent, whispered"
  }
}

4. Dynamic Evolution (`transition_soundscape`)

Crossfades two distinct environments for seamless scene transitions.

{
  "name": "transition_soundscape",
  "arguments": {
    "from_prompt": "Quiet library silence.",
    "to_prompt": "Sudden heavy rain on a tin roof.",
    "transition_duration": 8
  }
}

⚙️ Advanced Parameters

Parameter	Type	Description
`seed`	`Integer`	Ensures deterministic, reproducible audio outputs.
`image_path`	`String`	Multimodal: Uses a local image to guide the acoustic mood (e.g., resonance).
`bpm`	`Number`	Explicitly sets the rhythmic tempo (essential for music).
`intensity`	`Number`	1-10 scale controlling dynamic range and complexity.
`guidance`	`Number`	0.0-6.0 scale for prompt adherence (Lyria models).
`duration`	`Number`	Target length in seconds. Triggers the Seamless Looping Engine.

🔬 Architecture Overview

Gemini Audio MCP employs a unique Hybrid Engine Strategy:

WebSocket Loop: Connects to Gemini 2.5 Live for low-latency, interactive voice and foley tasks.
REST Pipeline: Interfaces with Lyria 3 Pro for high-fidelity musical synthesis.
PCM Processing: An internal Rust-based loop (decode -> crossfade -> loop -> encode) ensures that short clips are transformed into seamless, infinite soundscapes without audible clicks.

🧪 Troubleshooting

FFmpeg Errors

"FFmpeg not found": Ensure ffmpeg is in your system PATH. Run ffmpeg -version in your terminal to verify.
Transcoding Failures: Check if you have the necessary codecs (e.g., libmp3lame for MP3). Most standard FFmpeg installations include these.

API Issues

429 Rate Limit: The server implements a semaphore to limit concurrency, but ensure your API tier supports the requested model.
Empty Audio Output: Verify your GEMINI_API_KEY is correct and that your account has access to the requested model (especially lyria-3-pro-preview).

📄 License

Licensed under the MIT License. Engineered with precision by the MCP community.

Available Tools

9 tools

check_dependenciesB

Verifies that the system has required external tools like FFmpeg installed and accessible.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

B3.4/5.0

Behavior3/5

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

States what gets checked (installed/accessible) but lacks details on failure behavior or return structure since no annotations exist.

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

Conciseness5/5

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

Single front-loaded sentence with strong verb, no redundancy.

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

Completeness3/5

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

Adequate for simple tool but omits what constitutes success/failure without output schema to reference.

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?

Zero parameters per schema establishes baseline 4; no parameter semantics needed.

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

Purpose4/5

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

Clear specific action (verifies external tools) with concrete example (FFmpeg), functionally distinct from audio generation siblings.

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?

No guidance on when to invoke versus alternatives, or that it should precede generation tools requiring FFmpeg.

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

cleanup_assetsA

Manually trigger deletion of generated audio assets that exceed a certain age (in hours) to save disk space.

ParametersJSON Schema

Name	Required	Description	Default
`max_age_hours`	No	Files older than this will be deleted.

TDQS

A4.2/5.0

Behavior4/5

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

Effectively discloses destructive deletion behavior and manual nature without annotations, though omits irreversibility warnings.

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

Conciseness5/5

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

Single, well-structured sentence front-loaded with action; no redundant information.

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?

Adequately covers the simple operation given low complexity, though could clarify if deletion affects all asset types or specific formats.

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?

Meets baseline since schema has 100% description coverage; description mirrors but does not expand parameter semantics beyond 'certain age (in hours)'.

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?

Specific verb (deletion) and resource (generated audio assets) clearly distinguish this maintenance tool from sibling generation and playback tools.

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

Usage Guidelines4/5

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

Provides clear context (manual trigger to save disk space) but lacks explicit when-not guidance or alternative comparisons.

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

configureA

View or update persistent server settings like default audio format, sample rate, and automatic cleanup intervals. Call with no arguments to see current values.

ParametersJSON Schema

Name	Required	Description
`default_format`	No	Default file extension (e.g., 'mp3').
`default_duration`	No	Default duration for soundscapes in seconds.
`default_bitrate`	No
`default_sample_rate`	No
`default_channels`	No
`default_transition_duration`	No
`auto_cleanup_hours`	No	How often to clean up old audio files (in hours).

TDQS

A3.5/5.0

Behavior3/5

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

Discloses persistence and dual read/write modes, but lacks details on validation, side effects, or impact on concurrent operations.

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

Conciseness5/5

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

Two sentences, front-loaded with purpose; every clause provides necessary guidance without redundancy.

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

Completeness3/5

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

Adequate for basic invocation but omits return value structure (no output schema exists) and valid parameter ranges.

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?

Partially compensates for 43% schema coverage by grouping parameters into semantic categories (format, sample rate, cleanup), but omits duration and transition parameters.

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

Purpose4/5

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

Clear action (view/update) and resource (persistent server settings) with specific examples that distinguish it from audio generation siblings.

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

Usage Guidelines3/5

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

Provides explicit guidance for the empty-args viewing case but lacks explicit exclusions or alternatives versus sibling tools.

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

generate_musicA

Generates full songs, loops, or musical segments. Best for melodic content, rhythm, and structured compositions. (PAID MODELS - Pro: $0.08, Clip: $0.04).

ParametersJSON Schema

Name	Required	Description
`prompt`	Yes	Detailed description of the music (e.g., 'An upbeat jazz track with a fast tempo').
`model`	No	The Lyria model to use. 'lyria-3-pro-preview' (Full songs, $0.08) or 'lyria-3-clip-preview' (30s clips, $0.04). Defaults to Pro.
`format`	No	Output format (wav, mp3, flac).
`auto_play`	No

TDQS

A3.7/5.0

Behavior3/5

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

Discloses pricing ($0.08/$0.04) which is critical for paid models, but missing return value info, file persistence details, and rate limits (no annotations provided to cover these).

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?

Extremely concise and front-loaded; every sentence earns its place, though brevity comes at cost of missing behavioral details.

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?

Critical gap: no output schema exists and description fails to explain what is returned (file path, URL, binary data?) or auto_play behavior.

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 75% and adequately describes parameters; description adds minimal semantic value beyond schema except reinforcing the pricing model.

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?

Clearly states it generates songs/loops/segments and distinguishes from siblings (generate_sfx, generate_voice, generate_soundscape) by specifying 'melodic content, rhythm, and structured compositions'.

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

Usage Guidelines4/5

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

'Best for melodic content...' provides positive guidance for selection, though lacks explicit 'when not to use' or direct sibling comparisons.

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

generate_sfxA

Generates isolated, short-duration sound effects and foley (e.g., 'A laser blast' or 'Footsteps on gravel'). Best for specific one-shot audio cues. Uses Lyria-3-clip-preview ($0.04/req).

ParametersJSON Schema

Name	Required	Description
`prompt`	Yes	Description of the sound effect (e.g., 'A heavy metallic door slamming shut').
`format`	No	Output format (wav, mp3, flac).
`auto_play`	No

TDQS

A4.1/5.0

Behavior4/5

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

No annotations provided, but description compensates by disclosing specific model (Lyria-3-clip-preview) and pricing ($0.04/req), adding crucial operational context.

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

Conciseness5/5

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

Three tightly constructed sentences: purpose definition, usage guidance, and cost disclosure—each earns its place with no redundancy.

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

Completeness3/5

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

Adequate for tool complexity but missing return value specification (critical given no output schema exists to indicate what the tool produces).

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 67% schema coverage, description adds no parameter semantics; fails to explain undocumented 'auto_play' parameter or clarify expected prompt structure beyond schema.

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?

Clear specific verbs ('generates isolated, short-duration sound effects and foley') with concrete examples, and implicitly distinguishes from siblings (generate_music, generate_soundscape) via 'one-shot' and 'isolated' qualifiers.

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

Usage Guidelines4/5

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

'Best for specific one-shot audio cues' provides clear contextual guidance for when to select this over sibling audio tools, though lacks explicit 'when not to use' exclusions.

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

generate_soundscapeB

Generates immersive, high-quality environmental soundscapes (e.g., 'A rainy forest with distant thunder'). Best for background ambience and complex layered textures. Uses Gemini 2.0 Live.

ParametersJSON Schema

Name	Required	Description
`prompt`	Yes	The prompt describing the soundscape.
`duration`	No	Optional duration in seconds. Overrides default if provided.
`format`	No	Optional output format (wav, mp3, ogg, flac, etc.).
`bitrate`	No
`sample_rate`	No
`channels`	No
`auto_play`	No	If true, automatically plays the generated audio.

TDQS

B3.3/5.0

Behavior3/5

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

Discloses use of Gemini 2.0 Live model but omits other behavioral traits (rate limits, side effects, async nature) since annotations are absent.

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

Conciseness5/5

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

Compact three-sentence structure front-loaded with action, no redundancy, every sentence adds distinct value.

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

Completeness3/5

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

Adequate for basic invocation but leaves technical audio parameters unexplained given the moderate complexity of the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 57% schema coverage and missing descriptions for bitrate/sample_rate/channels, description fails to compensate for these technical audio parameters.

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

Purpose4/5

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

Clearly states it generates environmental soundscapes with specific examples, and distinguishes from siblings via 'background ambience' and 'complex layered textures' (vs music/SFX/voice).

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

Usage Guidelines3/5

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

Implies usage context via 'Best for background ambience' but lacks explicit when-not-to-use or alternative tool references.

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

generate_voiceA

Generates expressive speech and narration from text. Best for scripts, character dialogue, and narration. Uses Gemini 2.5 Native Audio.

ParametersJSON Schema

Name	Required	Description
`text`	Yes	The script or text to be read by the voice.
`voice_direction`	No	Optional instructions for the tone and style (e.g., 'Speak like a fast-talking auctioneer' or 'Use a whispery tone').
`format`	No	Optional output format (wav, mp3, ogg, flac, etc.).
`auto_play`	No	If true, automatically plays the generated audio.

TDQS

A3.8/5.0

Behavior3/5

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

Discloses underlying model (Gemini 2.5 Native Audio) hinting at capabilities, but omits side effects, persistence, rate limits, or resource management details.

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

Conciseness5/5

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

Extremely compact three-sentence structure with no redundancy; immediately establishes function and optimal use cases.

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?

Adequately covers purpose and implementation for a straightforward 4-parameter tool, though return value format remains unspecified.

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 is fully self-documenting (100% coverage); description adds no parameter-specific semantics but meets baseline expectations.

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

Purpose4/5

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

Clear specific action (generates speech/narration) and target content (scripts, dialogue), though explicit differentiation from sibling audio generators is implied rather than stated.

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

Usage Guidelines4/5

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

Provides positive usage guidance ('Best for scripts, character dialogue, and narration') but lacks explicit exclusions or references to alternative tools like generate_music.

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

play_audioA

Plays any local audio file using the system's default media player (e.g., 'afplay' on macOS).

ParametersJSON Schema

Name	Required	Description	Default
`path`	Yes	The absolute path to the audio file.

TDQS

A3.6/5.0

Behavior3/5

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

Discloses execution mechanism (system default player like 'afplay') but omits critical behavioral details like blocking vs. async behavior, error handling, or supported formats since no annotations exist.

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

Conciseness5/5

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

Single, efficient sentence that front-loads the verb and mechanism; no wasted words.

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?

Adequate for a simple single-parameter tool; explains the playback mechanism sufficiently given no output schema exists to document.

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 100% schema coverage, baseline is met; description reinforces 'local' constraint but adds no substantial semantic layer beyond the schema's 'absolute path' definition.

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

Purpose4/5

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

Clearly states it plays local audio files using the system default player, effectively distinguishing from sibling generation tools (generate_music, generate_sfx, etc.).

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

Usage Guidelines3/5

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

Implies usage for existing files via 'local audio file,' but lacks explicit when/when-not guidance contrasting with the generation siblings.

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

transition_soundscapeA

Generates two distinct soundscapes and creates a smooth crossfade transition between them. Ideal for evolving scenes or changing environments.

ParametersJSON Schema

Name	Required	Description
`from_prompt`	Yes
`to_prompt`	Yes
`transition_duration`	No	Duration of the crossfade in seconds. Defaults to config value.
`format`	No
`auto_play`	No	If true, automatically plays the generated audio.

TDQS

A3.7/5.0

Behavior3/5

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

No annotations provided; description mentions 'smooth crossfade' but omits critical behavioral details like output format, file persistence, or side effects given the auto_play parameter.

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

Conciseness5/5

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

Two concise sentences; front-loaded with core action, no redundancy, every clause earns its place.

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

Completeness3/5

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

Adequate for basic invocation but incomplete given lack of output schema and annotations; omits return value description and optional parameter implications (format, auto_play).

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 only 40% schema coverage, description implicitly clarifies from_prompt/to_prompt via 'two distinct soundscapes' but provides no semantic context for format, transition_duration, or auto_play.

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?

Specifically states it generates two soundscapes with a crossfade transition, clearly distinguishing from sibling generate_soundscape (single static) and play_audio.

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

Usage Guidelines3/5

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

Provides implied usage context ('Ideal for evolving scenes') but lacks explicit when-not-to-use guidance or comparison to single soundscape generation.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

9 tool updatesv0.1.0Apr 3, 2026
- First observedcheck_dependencies
- First observedcleanup_assets
- First observedconfigure
- First observedgenerate_music
- First observedgenerate_sfx
- First observedgenerate_soundscape
- First observedgenerate_voice
- First observedplay_audio
- First observedtransition_soundscape

Deploy Server

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

TDQS

A3.8/5.0

Scored 2026-04-04 00:39 across 9 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap. The four generation tools target different audio types (music, sfx, soundscape, voice), while utility tools handle distinct lifecycle phases (dependencies, configuration, cleanup, playback). Transition_soundscape is unambiguously a composite operation for scene changes.

Naming Consistency4/5

Strong adherence to snake_case verb_noun pattern (generate_music, cleanup_assets, play_audio). The only deviation is 'configure' which lacks a noun object, though this is idiomatic for settings management. All generation tools use consistent 'generate_' prefix.

Tool Count5/5

Nine tools is well-scoped for an audio generation server. The set covers four generation modes, configuration, dependency checking, playback, cleanup, and transitions without bloat. Each tool earns its place in the audio creation workflow.

Completeness4/5

Covers the full generation lifecycle with creation, playback, configuration, and cleanup capabilities. Minor gap in asset inventory management—there is no tool to list or retrieve specific generated assets by ID, only bulk cleanup by age, though agents may track assets themselves.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

mcp-producerOAuth
io.github.AceDataCloud
MCP server for Producer/Riffusion AI music generation
Audio Processing AI & Machine Learning
22
Gessa: game asset generation for AI agentsOAuth
ai.gessa
Generate game-ready 3D models, textures, and audio from natural language, over MCP.
AI & Machine Learning Image & Video Processing Audio Processing
1
StoryStudioOAuth
io.github.HelloElo-Fr
AI image, video, voice and music generation over MCP, routed to Veo 3.1, Seedance 2.0 and more.
AI & Machine Learning Image & Video Processing Audio Processing
1
mcp-veoOAuth
io.github.AceDataCloud
MCP server for Google Veo AI video generation
Multimedia Processing Image & Video Processing Entertainment & Media
23

Related MCP Servers

Gemini Gen MCP
AI & Machine Learning Audio Processing Image & Video Processing
ServiceStack
A
license
B
quality
C
maintenance
MCP server for generating images and audio using Google's Gemini AI models.
Updated 8 months ago (2026-01-19 13:37 UTC)
2
2
MIT
Talky Talky
Audio Processing Speech Processing AI & Machine Learning
shawnrushefsky
A
license
Not graded
quality
D
maintenance
A comprehensive audio MCP server that enables AI agents to generate speech, transcribe audio, clone voices, analyze speech quality, design soundscapes, and manage audio assets through a standardized interface.
Updated 8 months ago (2026-01-12 23:30 UTC)
2
MIT
multimodal-mcp
Image & Video Processing Audio Processing AI & Machine Learning
rsmdt
A
license
A
quality
C
maintenance
Multi-provider media generation MCP server that generates images, videos, audio, and transcriptions from text prompts using OpenAI, xAI, Gemini, ElevenLabs, and BFL through a single unified interface.
Updated 6 months ago (2026-03-05 20:02 UTC)
6
43 npm
1
MIT
Gemini MCP
AI & Machine Learning Image & Video Processing Speech Processing
moustafaezzeldeen-73
A
license
Not graded
quality
C
maintenance
Remote MCP server that exposes Google Gemini's text, image, video (Veo), and audio transcription capabilities as tools any MCP client can call directly.
Updated 3 months ago (2026-06-24 13:47 UTC)
78 npm
MIT

🎵 Gemini Audio MCP

🛠 Prerequisites

1. FFmpeg (Core Processing Engine)

2. Rust Toolchain (Compilation)

3. Node.js & NPM (Runtime)

🚀 Installation & Deployment

Global Installation (via NPX)

Manual Build (Optimized)

🔑 API Key Management

🎮 Tool Usage Guide

1. Environmental Generation (generate_soundscape)

2. Professional Music (generate_music)

3. Expressive Voice (generate_voice)

4. Dynamic Evolution (transition_soundscape)

⚙️ Advanced Parameters

🔬 Architecture Overview

🧪 Troubleshooting

FFmpeg Errors

API Issues

📄 License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

1. Environmental Generation (`generate_soundscape`)

2. Professional Music (`generate_music`)

3. Expressive Voice (`generate_voice`)

4. Dynamic Evolution (`transition_soundscape`)