Onur This workflow corresponds to n8n.io template #3052 — we link there as the canonical source.
This workflow follows the Chainllm → OpenAI Chat recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"meta": {
"templateCredsSetupCompleted": true
},
"nodes": [
{
"id": "e87d3723-7e7a-4ff3-bffb-b2bd2096bd34",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1080,
260
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "d25bf3ea-0de4-4317-9205-651f8a1a6ba8",
"name": "Basic LLM Chain",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1060,
40
],
"parameters": {
"text": "={{ $json.text }}",
"messages": {
"messageValues": [
{
"message": "=Okay, I've further refined the system prompt to include only the \"content\" and \"priority\" fields in the JSON output for the Todoist tool. Here's the updated prompt:\n\n**System Prompt:**\n\n```\nYou are an AI agent acting as a project management assistant. The user will provide you with a task or project description. Your job is to break down this task or project into smaller, manageable sub-tasks. You will then format each sub-task into a JSON object suitable for input to the \"Todoist\" tool and provide these JSON objects in a list.\n\n**Requirements:**\n\n1. **Sub-Task Decomposition:** Break down the task or project provided by the user into logical and actionable sub-tasks. Each sub-task should be self-contained, completable, and measurable.\n2. **JSON Format for Todoist:** Format each sub-task as a JSON object with the following structure:\n\n ```json\n {\n \"content\": \"[Task Description]\",\n \"priority\": [Priority Level (1-4, where 4 is highest)]\n }\n ```\n\n * `content`: A clear and concise description of the task.\n * `priority`: An integer representing the task priority, ranging from 1 (lowest) to 4 (highest). Consider the importance and urgency of the task when assigning the priority.\n\n3. **Tool Usage - Todoist JSON Output:** After decomposing the project into sub-tasks, you **MUST** format each sub-task into the JSON structure specified above and present all the JSON objects in a Python list. This list will be the direct input to the \"Todoist\" tool.\n\n4. **Contextual Understanding:** Fully understand the context of the task or project provided by the user. If necessary, ask for additional information or clarification to resolve any ambiguities.\n\n5. **Limitations:**\n\n * Avoid very general or abstract sub-tasks.\n * Ensure that each sub-task is completable and measurable.\n * When creating sub-tasks, consider the user's skills and resources.\n * Ensure all the output is valid JSON format within a python list\n\n**User Input:**\n\nThe user will provide you with a task or project description in the following format:\n\n```\nProject Description: [User's Entered Task or Project Description]\n```\n\n**Example:**\n\n**User Input:**\n\n```\nProject Description: Plan a team offsite.\n```\n\n**LLM Response:**\n\n```python\n[\n {\n \"content\": \"Research potential offsite locations.\",\n \"priority\": 3\n },\n {\n \"content\": \"Determine the budget for the offsite.\",\n \"priority\": 4\n },\n {\n \"content\": \"Send out a survey to gather team preferences.\",\n \"priority\": 3\n },\n {\n \"content\": \"Book the chosen venue.\",\n \"priority\": 4\n },\n {\n \"content\": \"Plan team-building activities.\",\n \"priority\": 2\n }\n]\n```\n\n**Key Changes and Explanations:**\n\n* **Simplified JSON Structure:** The JSON object now only includes `content` and `priority`.\n* **Example Updated:** The example response reflects the simplified JSON format.\n* **Conciseness:** The prompt is now more concise, focusing only on the necessary fields.\n\n**Jinja2 Template Version**\n\n```python\nfrom jinja2 import Template\n\ntemplate_string = \"\"\"\nYou are an AI agent acting as a project management assistant. The user will provide you with a task or project description. Your job is to break down this task or project into smaller, manageable sub-tasks. You will then format each sub-task into a JSON object suitable for input to the \"Todoist\" tool and provide these JSON objects in a list.\n\n**Requirements:**\n\n1. **Sub-Task Decomposition:** Break down the task or project provided by the user into logical and actionable sub-tasks. Each sub-task should be self-contained, completable, and measurable.\n2. **JSON Format for Todoist:** Format each sub-task as a JSON object with the following structure:\n\n ```json\n {\n \"content\": \"[Task Description]\",\n \"priority\": [Priority Level (1-4, where 4 is highest)]\n }\n ```\n\n * `content`: A clear and concise description of the task.\n * `priority`: An integer representing the task priority, ranging from 1 (lowest) to 4 (highest). Consider the importance and urgency of the task when assigning the priority.\n\n3. **Tool Usage - Todoist JSON Output:** After decomposing the project into sub-tasks, you **MUST** format each sub-task into the JSON structure specified above and present all the JSON objects in a Python list. This list will be the direct input to the \"Todoist\" tool.\n\n4. **Contextual Understanding:** Fully understand the context of the task or project provided by the user. If necessary, ask for additional information or clarification to resolve any ambiguities.\n\n5. **Limitations:**\n\n * Avoid very general or abstract sub-tasks.\n * Ensure that each sub-task is completable and measurable.\n * When creating sub-tasks, consider the user's skills and resources.\n * Ensure all the output is valid JSON format within a python list\n\n**User Input:**\n\nThe user will provide you with a task or project description in the following format:\n\n```\nProject Description: {{ project_description }}\n```\n\n**Example:**\n\n**User Input:**\n\n```\nProject Description: Plan a team offsite.\n```\n\n**LLM Response:**\n\n```python\n[\n {\n \"content\": \"Research potential offsite locations.\",\n \"priority\": 3\n },\n {\n \"content\": \"Determine the budget for the offsite.\",\n \"priority\": 4\n },\n {\n \"content\": \"Send out a survey to gather team preferences.\",\n \"priority\": 3\n },\n {\n \"content\": \"Book the chosen venue.\",\n \"priority\": 4\n },\n {\n \"content\": \"Plan team-building activities.\",\n \"priority\": 2\n }\n]\n```\n\"\"\"\n\ntemplate = Template(template_string)\n\n# Example Usage\nproject_description = \"Plan a team offsite.\"\nprompt = template.render(project_description=project_description)\n\nprint(prompt)\n```\n \n"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.5
},
{
"id": "ddfe59c5-574c-470b-b2cc-efa05da74972",
"name": "Receive Telegram Messages",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-220,
-100
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.1
},
{
"id": "23f2cedd-bcd2-4a94-acc1-8829b30553dc",
"name": "Voice or Text?",
"type": "n8n-nodes-base.switch",
"position": [
140,
-20
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "Audio",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "af30c479-4542-405f-b315-37c50c4e2bef",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.voice.file_id }}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "Text",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "a3ca8cd4-fbb2-40b5-829a-24724f2fbc85",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.text || \"\" }}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "Error",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "9bcfdee0-2f09-4037-a7b9-689ef392371d",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "error",
"rightValue": ""
}
]
},
"renameOutput": true
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "128e8268-a256-4256-8757-9ece8be86d75",
"name": "Fetch Voice Message",
"type": "n8n-nodes-base.telegram",
"position": [
500,
-120
],
"parameters": {
"fileId": "={{ $json.message.voice.file_id }}",
"resource": "file"
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "d8219ba5-bb33-44f5-a9a2-65fd16be335b",
"name": "Transcribe Voice to Text",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
720,
-120
],
"parameters": {
"options": {},
"resource": "audio",
"operation": "translate"
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.8
},
{
"id": "0c5f5568-fd14-4c65-8661-ebc5803158ce",
"name": "Prepare for LLM",
"type": "n8n-nodes-base.set",
"position": [
620,
100
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "b324a329-3c49-4f7f-b683-74331b7fe7f8",
"name": "=text",
"type": "string",
"value": "={{$json.message.text}}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "76ed8f5c-59f7-4cb9-9e59-25ac7e9e8c60",
"name": "Extract Tasks",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1220,
260
],
"parameters": {
"jsonSchemaExample": " {\n \"content\": \"Send out invitations.\",\n \"priority\": 3\n }"
},
"typeVersion": 1.2
},
{
"id": "7d0dbcb7-aac1-4eea-8f0b-6173148bfd3f",
"name": "Create Todoist Tasks",
"type": "n8n-nodes-base.todoist",
"position": [
1620,
40
],
"parameters": {
"content": "={{ $json.output.content }}",
"options": {
"priority": "={{ $json.output.priority }}"
},
"project": {
"__rl": true,
"mode": "list",
"value": "2349786654",
"cachedResultName": "Task"
}
},
"credentials": {
"todoistApi": {
"name": "<your credential>"
}
},
"typeVersion": 2.1
},
{
"id": "544b3f63-8ac1-4f81-9c24-943df16d9324",
"name": "Send Confirmation",
"type": "n8n-nodes-base.telegram",
"position": [
1880,
40
],
"parameters": {
"text": "=Task : {{ $json.content }} Task Link :{{ $json.url }}",
"chatId": "={{ $('Receive Telegram Messages').item.json.message.chat.id }}",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "b244f935-3047-4581-84ac-b01b2f962c1d",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-260,
-240
],
"parameters": {
"width": 260,
"height": 320,
"content": " \n**This workflow listens for incoming voice or text messages from Telegram users.** "
},
"typeVersion": 1
},
{
"id": "fa99930d-8e75-4f1e-aa9b-47c38e611538",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
440,
-220
],
"parameters": {
"width": 460,
"height": 260,
"content": " **Voice messages are fetched from Telegram and transcribed into text using OpenAI's Whisper API.** "
},
"typeVersion": 1
},
{
"id": "beb460c9-0412-40c4-a3cf-76660eb0e1b8",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
1000,
-60
],
"parameters": {
"width": 380,
"height": 440,
"content": " \n**The LLM (OpenAI Chat Model) analyzes the text and breaks it down into tasks and sub-tasks, formatted for Todoist.** "
},
"typeVersion": 1
}
],
"connections": {
"Extract Tasks": {
"ai_outputParser": [
[
{
"node": "Basic LLM Chain",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Voice or Text?": {
"main": [
[
{
"node": "Fetch Voice Message",
"type": "main",
"index": 0
}
],
[
{
"node": "Prepare for LLM",
"type": "main",
"index": 0
}
]
]
},
"Basic LLM Chain": {
"main": [
[
{
"node": "Create Todoist Tasks",
"type": "main",
"index": 0
}
]
]
},
"Prepare for LLM": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Fetch Voice Message": {
"main": [
[
{
"node": "Transcribe Voice to Text",
"type": "main",
"index": 0
}
]
]
},
"Create Todoist Tasks": {
"main": [
[
{
"node": "Send Confirmation",
"type": "main",
"index": 0
}
]
]
},
"Transcribe Voice to Text": {
"main": [
[
{
"node": "Basic LLM Chain",
"type": "main",
"index": 0
}
]
]
},
"Receive Telegram Messages": {
"main": [
[
{
"node": "Voice or Text?",
"type": "main",
"index": 0
}
]
]
}
}
}
Credentials you'll need
Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.
openAiApitelegramApitodoistApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This n8n workflow empowers you to seamlessly manage your tasks by creating Todoist entries directly from Telegram, using the power of AI. Simply send a voice or text message to your Telegram bot, and this workflow will transform it into actionable tasks in your Todoist account.
Source: https://n8n.io/workflows/3052/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This workflow is for users who want to turn Telegram into a personal AI-powered assistant capable of handling everyday tasks through natural language. It's ideal for solo founders, operators, or profe
Memory Buffer Window, Tool Workflow, Tool Think +9
This n8n template demonstrates how to create authentic-looking User Generated Content (UGC) advertisements using AI image generation, voice synthesis, and lip-sync technology. The workflow transforms
Chain Llm, Output Parser Structured, Agent +5
📌 How it works
Telegram Trigger, Telegram, OpenAI +5
This workflow gives you the ability to reply to a long email with a voice note, rather than having to type everything out.
Output Parser Structured, OpenAI Chat, Telegram +5
-Personal or family budget tracking.
OpenAI Chat, Output Parser Structured, Chain Llm +4