Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEVICENoDevice to use: cuda or cpucuda
HF_TOKENNoOnly if WhisperX VAD asks for it
MIN_SILENCENoMin gap (s) that counts as a clean cut boundary0.15
SNAP_MARGINNoHow far (s) into the silence to place the cut (capped at gap/2)0.08
STT_BACKENDNoBackend for speech-to-text: whisperx (free, local) or openai (whisper-1)whisperx
COMPUTE_TYPENoCTranslate2 compute typefloat16
CROSSFADE_MSNoPer-join audio fade to kill clicks (0 = off)15
OPENAI_API_KEYNoRequired only for the openai backend
WHISPERX_MODELNoWhisperX model sizelarge-v3
WORKSPACE_ROOTNoWhere project data is stored./workspaces

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ElliotTheGreek/short-form-video-editor-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server