Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AWS_REGIONNoAWS region used for Amazon Transcribe, Amazon Polly and Amazon Bedrock.
FR_PROFILENoDeployment profile: `aws` (Amazon Transcribe for speech-to-text, Amazon Polly for text-to-speech, Amazon Bedrock Nova 2 Lite as the LLM), `local` (on-device silero VAD + sherpa-onnx STT/TTS, Bedrock for the LLM only), `gpu` (Qwen3-ASR + VoxCPM2 on a GPU spot) or `demo` (stand-in speaker module driven by the 'Speaking now' switch, browser speech).
FR_LOCAL_MODELSNoDirectory containing the models downloaded beforehand (silero VAD, familyvoice ResNet34-LM int8, sherpa-onnx parakeet/Moonshine/SenseVoice, Piper voice). Used with FR_PROFILE=local, which downloads nothing at run time.
AWS_ACCESS_KEY_IDNoAWS credentials with permissions for Amazon Transcribe, Amazon Polly and Amazon Bedrock (required by the default `aws` profile).
FR_LLM_AUDIO_INPUTNoSends the audio to the LLM side as well, so a speech-to-speech model (e.g. Amazon Nova 2.5 Sonic) could replace STT+LLM+TTS.
AWS_SECRET_ACCESS_KEYNoAWS credentials with permissions for Amazon Transcribe, Amazon Polly and Amazon Bedrock (required by the default `aws` profile).
FR_NOTIFY_WEBHOOK_URLNoWebhook URL that receives message delivery receipts (heard or faded unheard) in addition to the sender's phone notification.

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