Schema | Claude Telegram Supercharged

Claude Telegram Supercharged

Describes the environment variables required to run the server.

Name	Required	Description
`OPENAI_API_KEY`	No	OpenAI API key used for Whisper voice-message transcription (recommended, fastest and highest quality), set in ~/.claude/channels/telegram/.env. No local install needed.
`autoTranscribe`	No	When enabled (the default), the server transcribes all voice/audio messages in group chats, even ones that don't mention the bot. Toggle with /telegram:access set autoTranscribe true\|false.
`TELEGRAPH_ENABLED`	No	Enable Telegraph (telegra.ph) Instant View publishing for long content (3000+ chars). Disabled by default because posts are publicly accessible by URL. Set to true to opt in.
`TELEGRAM_BOT_TOKEN`	Yes	The bot token from BotFather (e.g. 123456789:AAHfiqksKZ8...). Written to ~/.claude/channels/telegram/.env by /telegram:configure, can also be written by hand or set in the shell environment (shell takes precedence). The server won't connect without it.
`OPENAI_WHISPER_MODEL`	No	Transcription model to use, e.g. whisper-1 (default, $0.006/min) or gpt-4o-transcribe.
`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 escalation. Complex tasks auto-escalate to Opus via subagents by default; change the target with this variable.

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