Gemini Audio MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Your Gemini API key from Google AI Studio |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| 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. |
| generate_voiceA | Generates expressive speech and narration from text. Best for scripts, character dialogue, and narration. Uses Gemini 2.5 Native Audio. |
| 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). |
| 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). |
| transition_soundscapeA | Generates two distinct soundscapes and creates a smooth crossfade transition between them. Ideal for evolving scenes or changing environments. |
| 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. |
| play_audioA | Plays any local audio file using the system's default media player (e.g., 'afplay' on macOS). |
| cleanup_assetsA | Manually trigger deletion of generated audio assets that exceed a certain age (in hours) to save disk space. |
| check_dependenciesB | Verifies that the system has required external tools like FFmpeg installed and accessible. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
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.
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.
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.
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.