Schema | Claude Telegram Supercharged

Claude Telegram Supercharged

Describes the environment variables required to run the server.

Name	Required	Description	Default
`OPENAI_API_KEY`	No	Your OpenAI API key (`sk-proj-...`) used for Whisper voice-message transcription. Set in `~/.claude/channels/telegram/.env`. Recommended transcription method -- fastest, highest quality, non-blocking. Optional if using a local whisper fallback.
`TELEGRAPH_ENABLED`	No	Enable publishing of long-form content to Telegraph (telegra.ph) as Instant View articles. Disabled by default because posts are publicly accessible by URL. Set to `true` in `~/.claude/channels/telegram/.env` to enable.	false
`TELEGRAM_BOT_TOKEN`	Yes	The Telegram bot token from BotFather (looks like `123456789:AAHfiqksKZ8...`). Written to `~/.claude/channels/telegram/.env` by `/telegram:configure`, or set in your shell environment (shell takes precedence). The server won't connect without this.
`OPENAI_WHISPER_MODEL`	No	OpenAI transcription model to use. Defaults to `whisper-1` ($0.006/min); can be switched to 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 for auto-escalation of complex tasks via subagents (defaults to Opus).

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

ResponsivenessNo issues