Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.definable.ai/llms.txt

Use this file to discover all available pages before exploring further.

Build a Telegram bot with tools, memory, and voice note transcription.
1

Create the bot

Open Telegram and message @BotFather:
  1. Send /newbot
  2. Choose a name and username
  3. Copy the bot token
2

Create the agent

telegram_bot.py
import asyncio
import os
from definable.agent import Agent
from definable.agent.interface import TelegramInterface
from definable.memory import Memory, SQLiteStore
from definable.tool.decorator import tool

@tool
def get_weather(city: str) -> str:
    """Get the current weather for a city."""
    return f"Sunny, 24C in {city}"

agent = Agent(
    model="gpt-4o",
    instructions="You are a helpful Telegram assistant with weather tools.",
    tools=[get_weather],
    memory=Memory(store=SQLiteStore("./telegram_memory.db")),
    audio_transcriber=True,  # Transcribe voice notes via Whisper
)

interface = TelegramInterface(
    agent=agent,
    bot_token=os.environ["TELEGRAM_BOT_TOKEN"],
)

asyncio.run(interface.serve_forever())
3

Install dependencies

pip install definable
4

Set environment variables

export TELEGRAM_BOT_TOKEN="123456:ABC-DEF..."
export OPENAI_API_KEY="sk-..."
5

Run

python telegram_bot.py
Open Telegram, find your bot, and start chatting. The bot:
  • Calls the weather tool when asked about weather
  • Remembers conversations across messages
  • Transcribes voice notes to text automatically

​
Production Deployment

For production, switch to webhook mode: 
interface = TelegramInterface(
    agent=agent,
    bot_token=os.environ["TELEGRAM_BOT_TOKEN"],
    mode="webhook",
    webhook_url="https://your-domain.com/webhook/telegram",
    webhook_secret=os.environ.get("WEBHOOK_SECRET"),
    max_concurrent_requests=20,
)
See Telegram reference for all configuration options.