Skip to main content
Glama
kanaworksai-hue

That's one sentence; but the instruction is no more than 2 sentences, so 2 is fine. Let me make it two sentences for clarity.

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AUDIO_STUDIO_FFMPEGNoPath to ffmpegffmpeg on PATH
AUDIO_STUDIO_BACKENDNoauto or sa3-mlxauto
AUDIO_STUDIO_SA3_DIRNoUse another stable-audio-3 checkout<repo>/vendor/stable-audio-3
AUDIO_STUDIO_SA3_MODELNomedium (best quality, up to 380 s), sm-music or sm-sfx (small and fast, up to 120 s)medium
AUDIO_STUDIO_OUTPUT_DIRNoWhere audio files are written<repo>/outputs
AUDIO_STUDIO_MLX_CACHE_GBNoCap on MLX's buffer cache. Without it, a long generation can leave ~6 GB cached1
AUDIO_STUDIO_IDLE_UNLOAD_MINNoFree the models after this many idle minutes (0 = never)10

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

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources