YouTube to Telegram, instant TL;DW summaries
You paste a YouTube link, tell yourself you’ll “watch it later,” and then… it sits there. Or you do watch it, but the notes are messy, the best quote is gone, and you can’t find the one tool they mentioned at minute 47.
This YouTube TL;DW automation hits marketing managers hardest during competitor research. But founders trying to learn fast and students turning lectures into study notes feel the same drag. The outcome is simple: structured, searchable summaries in Telegram without rewatching everything.
You’ll see how the workflow grabs the transcript, pulls video metadata, generates a clean TL;DW with chapters and quotes, and sends it back to Telegram in readable chunks.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: YouTube to Telegram, instant TL;DW summaries
flowchart LR
subgraph sg0["Telegram Message Flow"]
direction LR
n0["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Fetch Transcript via API"]
n1["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/code.svg' width='40' height='40' /></div><br/>Derive Transcript Text"]
n2["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>Retrieve Video Metadata"]
n3["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/code.svg' width='40' height='40' /></div><br/>Parse Video Details"]
n4@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Validate YouTube Link", pos: "b", h: 48 }
n5["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Send Invalid Link Notice"]
n6["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Dispatch Processing Note"]
n7["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Telegram Message Trigger"]
n8@{ icon: "mdi:swap-vertical", form: "rounded", label: "Assign Video Settings", pos: "b", h: 48 }
n9@{ icon: "mdi:robot", form: "rounded", label: "Create TLDR Summary", pos: "b", h: 48 }
n10@{ icon: "mdi:brain", form: "rounded", label: "Gemini Flash Model", pos: "b", h: 48 }
n11["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/merge.svg' width='40' height='40' /></div><br/>Combine Summary Data"]
n15["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/code.svg' width='40' height='40' /></div><br/>Format Summary Segments"]
n16@{ icon: "mdi:swap-vertical", form: "rounded", label: "Iterate Message Chunks", pos: "b", h: 48 }
n17["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Send Summary Segment"]
n18@{ icon: "mdi:cog", form: "rounded", label: "Throttle Delay", pos: "b", h: 48 }
n19["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Send Video Overview"]
n10 -.-> n9
n9 --> n11
n7 --> n4
n3 --> n11
n17 --> n18
n1 --> n9
n18 --> n16
n15 --> n16
n4 --> n6
n4 --> n5
n6 --> n8
n16 --> n17
n11 --> n19
n11 --> n15
n8 --> n0
n8 --> n2
n2 --> n3
n0 --> n1
end
subgraph sg1["Error Event Flow"]
direction LR
n12["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>Notify Admin Channel"]
n13["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/code.svg' width='40' height='40' /></div><br/>Compose Error Report"]
n14@{ icon: "mdi:play-circle", form: "rounded", label: "Error Event Trigger", pos: "b", h: 48 }
n14 --> n13
n13 --> n12
end
%% Styling
classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
classDef disabled stroke-dasharray: 5 5,opacity: 0.5
class n7,n14 trigger
class n9 ai
class n10 aiModel
class n4 decision
class n0,n2 api
class n1,n3,n15,n13 code
classDef customIcon fill:none,stroke:none
class n0,n1,n2,n3,n5,n6,n7,n11,n15,n17,n19,n12,n13 customIcon
The Problem: YouTube Research Eats Your Week
Watching long YouTube videos for “just one insight” is a trap. You start at 1.25x speed, pause to write notes, rewind because you missed a tool name, then lose your place when Slack pings. Later, when you need that exact framework or quote, you’re scrubbing the timeline again, hoping you remember the right chapter. It’s not only slow. It’s mentally expensive, and the work is weirdly fragile because your notes depend on you catching everything in real time.
It adds up fast. Here’s where it breaks down in real life.
- Manual note-taking turns a 2-hour video into a half-day task once you include rewinding, formatting, and saving it somewhere useful.
- Important details get lost, especially tool names, timestamps, and quotable lines that you want to reuse in content or internal docs.
- Teams don’t share learnings well because one person’s notes live in Notion, another person’s are in a Google Doc, and the original link has no structure.
- Existing “summarizer” tools often miss context because they don’t pull full transcripts and metadata reliably.
The Solution: Send a Link, Get a Structured TL;DW
This workflow turns Telegram into your “dropbox for video knowledge.” You send a YouTube URL to a Telegram bot, and n8n validates the link so you don’t waste time on bad inputs. Then it fetches the full transcript and the video’s metadata (title, channel, duration, tags, chapters, and more) through Decodo’s scraping API. Once the transcript is cleaned, Google Gemini Flash generates a structured TL;DW that’s actually usable, not a vague paragraph. Finally, the workflow merges the AI summary with the metadata, formats everything into Telegram-friendly chunks, and sends you a video overview plus the full summary in a clean sequence.
It starts with a Telegram message trigger. From there, transcript and metadata are pulled in parallel so you are not waiting on two slow steps in a row. The output lands back in Telegram as a readable overview and a TL;DW broken into messages that fit Telegram’s limits.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say your agency reviews 50 competitor videos a month and each one averages about 90 minutes. Manually, even “skimming” and taking usable notes can take about 2 hours per video once you include pauses and rewinds, so you’re looking at roughly 100 hours. With this workflow, you drop each link into Telegram (maybe 1 minute each) and get the TL;DW back in about a minute. That’s still time spent reading, but most teams end up closer to 6–10 hours total for the month, not 100.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Telegram Bot API for receiving links and replying.
- Decodo Scraper API to extract transcripts and metadata.
- Google Gemini API key (get it from Google AI Studio).
Skill level: Beginner. You’ll connect a few accounts, paste API keys, and edit one or two settings like language.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
A Telegram message kicks it off. You send a youtube.com or youtu.be link to your bot, and the workflow checks it’s valid before doing anything expensive.
Transcript and metadata are collected in parallel. n8n extracts the video ID, then calls Decodo to fetch the transcript and video details at the same time, so the wait is usually short.
The summary gets generated and structured. The transcript is cleaned, then Gemini Flash creates the TL;DW with chapters, key points, tools mentioned, practical takeaways, and notable quotes.
Telegram receives a neat, readable output. The workflow merges the summary with metadata, formats it into chunks (so messages don’t get cut off), throttles delivery slightly, and posts both the overview card and the full TL;DW.
You can easily modify the summary format to match your note style (or your team’s template) based on your needs. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Telegram Message Trigger
Set up the workflow to start when a Telegram message is received and validate incoming YouTube links.
- Add Telegram Message Trigger and enable updates for message.
- Credential Required: Connect your telegramApi credentials in Telegram Message Trigger.
- Configure Validate YouTube Link with two conditions: contains
youtube.and containsyoutu.beusing{{ $json.message.text }}. - Set the invalid-link path to Send Invalid Link Notice with Text set to
not a youtube urland Chat ID set to{{ $('Telegram Message Trigger').item.json.message.chat.id }}. - Credential Required: Connect your telegramApi credentials in Send Invalid Link Notice.
youtu.be so Validate YouTube Link routes to processing.
Step 2: Connect YouTube Data Sources
Extract the video ID and trigger parallel API calls for transcript and metadata.
- Configure Dispatch Processing Note to send
<i>Processing your input...</i>with Chat ID set to{{ $('Telegram Message Trigger').item.json.message.chat.id }}. - Credential Required: Connect your telegramApi credentials in Dispatch Processing Note.
- In Assign Video Settings, set videoId to
{{ $('Telegram Message Trigger').item.json.message.text.match(/youtu\.be\/([^?]+)/)[1] }}and languageCode toen. - Assign Video Settings outputs to both Fetch Transcript via API and Retrieve Video Metadata in parallel.
- In Fetch Transcript via API, set URL to
https://scraper-api.decodo.com/v2/scrape, Method toPOST, and body parameterstarget: youtube_transcript,query: {{ $json.videoId }},language_code: {{ $json.languageCode }}. - Credential Required: Connect your httpHeaderAuth credentials in Fetch Transcript via API.
- In Retrieve Video Metadata, set URL to
https://scraper-api.decodo.com/v2/scrape, Method toPOST, and body parameterstarget: youtube_metadata,query: {{ $json.videoId }}. - Credential Required: Connect your httpHeaderAuth credentials in Retrieve Video Metadata.
youtu.be format. Add a second extraction rule if you expect full youtube.com/watch URLs.
Step 3: Set Up Transcript Parsing and AI Summary
Transform transcript data into a single text block and generate a TLDR summary with Gemini.
- Leave the JavaScript in Derive Transcript Text as-is to output
transcript,textArray, andtotalSegments. - Configure Create TLDR Summary with Text set to
{{ $json.transcript }}and keep the prompt as defined. - Gemini Flash Model is connected as the language model for Create TLDR Summary — ensure credentials are added to Gemini Flash Model, not the chain node.
- Credential Required: Connect your googlePalmApi credentials in Gemini Flash Model.
Step 4: Configure Summary Assembly and Parallel Outputs
Merge metadata and summary, then send the overview and format chunked messages in parallel.
- In Parse Video Details, keep the JavaScript intact to produce fields like
title,duration, andsummaryForAI. - Configure Combine Summary Data with Mode set to
combineand Combine By set tocombineAll. - Combine Summary Data outputs to both Send Video Overview and Format Summary Segments in parallel.
- In Send Video Overview, set Text to
=📺 Youtube Video Analyze of **{{ $json.title }}** by **{{ $json.channel }}** ⏱️ Video Duration: {{ $json.duration }} {{ $json.summaryForAI.content }} Stats: {{ $json.summaryForAI.stats }} Chapters (if applicable) {{ $json.summaryForAI.structure }}and Chat ID to{{ $('Telegram Message Trigger').item.json.message.chat.id }}. - Credential Required: Connect your telegramApi credentials in Send Video Overview.
- Keep Format Summary Segments JavaScript intact to split output into 4,000-character HTML chunks and include
parseMode: 'HTML'.
Step 5: Configure Chunked Delivery and Throttling
Send each summary segment to Telegram with throttling to avoid rate limits.
- Connect Format Summary Segments to Iterate Message Chunks and ensure batching is enabled.
- In Send Summary Segment, set Text to
{{ $json.text }}and Chat ID to{{ $('Telegram Message Trigger').item.json.message.chat.id }}. - Credential Required: Connect your telegramApi credentials in Send Summary Segment.
- Set Throttle Delay to Amount
1to add a one-second pause between messages. - Wire Send Summary Segment → Throttle Delay → Iterate Message Chunks to loop through all chunks.
maxCharsPerChunk at 4000 to avoid failed sends.
Step 6: Add Error Handling
Capture workflow errors and send a formatted report to your admin channel.
- Use Error Event Trigger to listen for workflow errors.
- Keep the error formatting logic in Compose Error Report to generate a compact HTML message.
- In Notify Admin Channel, set Text to
{{ $json.message }}and replace Chat ID[YOUR_ID]with your admin channel ID. - Credential Required: Connect your telegramApi credentials in Notify Admin Channel.
Step 7: Test and Activate Your Workflow
Validate the full flow from Telegram input to summary delivery, then enable the workflow.
- Click Execute Workflow and send a YouTube link to your Telegram bot.
- Confirm you receive Dispatch Processing Note, then the Send Video Overview message and multiple Send Summary Segment chunks.
- Verify the parallel paths run: Combine Summary Data feeds both Send Video Overview and Format Summary Segments simultaneously.
- Trigger an error (e.g., invalid API key) and confirm Notify Admin Channel receives a formatted alert.
- Toggle the workflow to Active for production use.
Common Gotchas
- Telegram Bot API credentials can expire or be pasted wrong. If replies stop, check the bot token in your n8n Telegram credentials first, then confirm the bot is still active in BotFather.
- If you’re using Wait nodes or external processing, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
- Decodo Scraper API 401/403 errors are usually a bad or expired key. Check the HTTP Header Auth credential (“Authorization”) and regenerate the key in the Decodo dashboard if needed.
Frequently Asked Questions
About 30 minutes if you already have the API keys.
No. You’ll mostly paste credentials and tweak a prompt.
Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in Decodo and Google Gemini API usage costs.
Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.
Yes, and it’s one of the easiest edits. Change the languageCode setting in the “Set: Video ID & Config” node so Decodo requests the right caption language. Then adjust the “Generate TLDR” prompt so Gemini formats headings and tone the way you want. Common tweaks include a more technical summary, a beginner-friendly version, or “tools-only” extraction for faster competitive research.
Usually it’s a bad bot token or the wrong chat ID in the admin alert node. Regenerate the token in BotFather if you’re unsure, then update the Telegram credentials in n8n. If error alerts aren’t arriving, grab your user ID (many people use @userinfobot) and replace the value in the “Alert Admin” configuration. Also check that the bot is allowed to post in the chat where you’re testing, especially in groups.
A lot, within reason. On n8n Cloud, the practical limit is your monthly executions and how many videos you process per day, while self-hosting has no execution cap (it depends on your server). The workflow itself processes one video per run, and most runs finish in under a couple minutes unless the transcript is huge or the APIs are slow. If you plan to do hundreds a day, add rate limiting and store results (Google Sheets is already in the workflow, so you’re close). Your main constraint will be API quotas and cost, not n8n logic.
Often, yes, because this flow benefits from parallel API calls, message chunking, and more detailed error handling than basic “trigger → action” automations. n8n also gives you a self-host option, which matters when you’re processing lots of videos. Zapier or Make can still work if you want something extremely simple and don’t care about transcript cleaning or structured outputs. If you’re torn, Talk to an automation expert and you’ll get a straight answer based on volume and workflow complexity.
Once it’s running, you stop treating YouTube like a time sink and start treating it like a searchable knowledge feed in Telegram. Honestly, that shift alone is worth the setup.
Need Help Setting This Up?
Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.