Skip to main content
Glama
alandyallworwor-cmd

ElevenLabs Audio MCP for ChatGPT

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP port; Railway supplies this automatically.3000
DATA_DIRNoOptional preference storage override. Railway volumes are detected automatically through RAILWAY_VOLUME_MOUNT_PATH.
MAX_TEXT_LENGTHNoMaximum characters accepted per generation.5000
MCP_PATH_SECRETYesRequired 24–128 character URL-safe secret.
PUBLIC_BASE_URLNoOptional canonical public origin.
AUDIO_TTL_SECONDSNoHow long generated audio remains available.900
ELEVENLABS_API_KEYYesRequired ElevenLabs API key.
ELEVENLABS_MODEL_IDNoDefault TTS model. Eleven v3 gives the model the most expressive delivery controls.eleven_v3
ELEVENLABS_VOICE_IDYesRequired ElevenLabs voice ID used when a tool call omits voice_id; users can override it through the saved preference.
MAX_CACHED_AUDIO_BYTESNoMaximum total in-memory audio cache.52428800
MAX_CONCURRENT_GENERATIONSNoMaximum simultaneous TTS requests.2
MAX_GENERATIONS_PER_MINUTENoPer-instance burst limit protecting ElevenLabs credits.10

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/alandyallworwor-cmd/MCP_Eleven'

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