Social Whisper Transcript MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_TOKEN | Yes | Bearer token for the REST API and MCP; also signs download links. Compose refuses to start without one. | |
| PRELOAD_MODEL | No | Load the default model at startup. Default: false. | |
| WHISPER_MODEL | No | Whisper model to use: large-v3-turbo, large-v3, medium, or small. Default: large-v3-turbo. | |
| PUBLIC_BASE_URL | No | Base for download links, e.g. behind a reverse proxy or tunnel. Default: address the client used. | |
| WHISPER_THREADS | No | CPU threads per job. Default: CPUs, max 8. | |
| ALLOW_PRIVATE_URLS | No | Allow links to localhost / LAN addresses. Default: false. | |
| IDLE_UNLOAD_SECONDS | No | Free model RAM after this idle time; 0 = keep loaded. Default: 600. | |
| MAX_DURATION_SECONDS | No | Longest video accepted (4 h). Default: 14400. | |
| WAIT_TIMEOUT_SECONDS | No | Max blocking time for "wait": true. Default: 600. | |
| DOWNLOAD_LINK_TTL_SECONDS | No | How long signed download links work. Default: 86400. |
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
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues