local-whisper-speech-to-text
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Listening interface. | 0.0.0.0 |
| PORT | No | Listening port. | 8000 |
| DATA_DIR | No | Data root: audio inputs and job state. | ./data |
| API_TOKEN | No | Bearer token required by REST and MCP. Empty means no authentication. | |
| HTTP_TIMEOUT | No | Maximum time to download audio, in seconds. | 60 |
| MAX_INPUT_SIZE | No | Maximum audio file size, in bytes (500 MiB). | 524288000 |
| WHISPER_DEVICE | No | Device passed to faster-whisper (cpu, cuda, auto). | cpu |
| CALLBACK_TIMEOUT | No | Maximum time for the callback POST, in seconds. | 30 |
| ALLOWED_URL_HOSTS | No | Comma-separated allow-list of hosts permitted for audio. | |
| ALLOW_PRIVATE_URLS | No | Allow audio URLs pointing at private IP addresses. | false |
| WHISPER_COMPUTE_TYPE | No | Quantisation (int8, float16, float32). | int8 |
| ALLOWED_CALLBACK_HOSTS | No | Comma-separated allow-list of hosts permitted for callbacks. | |
| ALLOW_PRIVATE_CALLBACKS | No | Allow callback URLs pointing at private IP addresses. | false |
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 issues