Schema | Claude Telegram Supercharged

Claude Telegram Supercharged

Describes the environment variables required to run the server.

Name	Required	Description	Default
`OPENAI_API_KEY`	No	OpenAI API key used for Whisper transcription (recommended method, fastest, highest quality, non-blocking). Set in `~/.claude/channels/telegram/.env` as `OPENAI_API_KEY=sk-proj-...`. If absent, the server falls back to local whisper.cpp, openai-whisper, or no transcriber.
`TELEGRAPH_ENABLED`	No	Set to `true` to enable publishing long-form content to Telegraph (telegra.ph). Disabled by default because posts are publicly accessible by URL.	false
`TELEGRAM_BOT_TOKEN`	Yes	The bot token from BotFather (looks like 123456789:AAHfiqksKZ8...). Set via `/telegram:configure 123456789:AAHfiqksKZ8...`, written to `~/.claude/channels/telegram/.env` as `TELEGRAM_BOT_TOKEN=...`, or set in your shell environment (shell takes precedence).
`OPENAI_WHISPER_MODEL`	No	The OpenAI transcription model to use. Defaults to `whisper-1` ($0.006/min); can be switched, e.g. `gpt-4o-transcribe`.	whisper-1
`TELEGRAM_ROUTER_MODEL`	No	Configurable router model for two-tier model routing: Haiku (fast, 200K), Sonnet (balanced, 1M), or Opus (deep, 1M).
`TELEGRAM_ESCALATION_MODEL`	No	Target model that complex tasks auto-escalate to via subagents (change the escalation target).

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityActive

ResponsivenessResponsive