Transcribe & analyze Telegram voice messages with AssemblyAI & GPT-4.1 to Gmail

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Telegram Voice → AI Summary & Sentiment Analysis via Gmail This n8n template demonstrates how to capture Telegram voice messages, transcribe them into text using AssemblyAI, analyze the transcript ...

Best for

AI Summarization automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.telegram, n8n-nodes-base.wait, n8n-nodes-base.if, n8n-nodes-base.stickynote, n8n-nodes-base.httprequest, n8n-nodes-base.switch, @n8n/n8n-nodes-langchain.openai, n8n-nodes-base.gmail

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Sridevi Edupuganti.

Original n8n.io source

1.1 Workflow description

Title: Transcribe & analyze Telegram voice messages with AssemblyAI & GPT-4.1 to Gmail
Workflow name: Transcribe & analyze Telegram voice messages with AssemblyAI & GPT-4.1 to Gmail

Telegram Voice → AI Summary & Sentiment Analysis via Gmail

This n8n template demonstrates how to capture Telegram voice messages, transcribe them into text using AssemblyAI, analyze the transcript with AI for summary and sentiment insights, and finally deliver a structured email report via Gmail.

Use cases

Automating meeting or lecture voice note transcriptions.
Gathering student feedback or training session insights from voice messages.
Quickly summarizing Telegram-delivered audio inputs into structured reports.
Reducing manual effort in capturing sentiment and key action items from conversations.

How it works

A voice message is sent to a connected Telegram Bot.
The workflow fetches the file and uploads it to AssemblyAI.
AssemblyAI generates a transcript from the audio.
The transcript is analyzed by OpenAI to extract:
- Executive summary (120–180 words)
- Sentiment label and score
- Key points
- Action items (if any)
- Notable quotes
- Topics
The formatted analysis is sent as an email report using Gmail.
The workflow ends with a clean summary email containing actionable insights.

How to use

Import this workflow into your n8n instance.
Set up and connect the required credentials:
- Telegram Bot API token
- AssemblyAI API key
- OpenAI API key
- Gmail OAuth2 account
Replace placeholders (e.g., <<YOUR_EMAIL ID>> and <<YOUR_ASSEMBLYAI_API_KEY>>) with your actual values.
Start the workflow. Whenever a voice message is received on the Telegram Bot, the workflow will process it end-to-end and deliver a polished email report.

Requirements

Telegram Bot account (API token)
AssemblyAI account with API key
OpenAI account with API key
Gmail OAuth2 credentials configured in n8n
Active n8n instance

Customising this workflow

You can customize the email formatting, sentiment thresholds, or extend the workflow to save transcripts into Google Drive, Airtable, or any other connected apps. Additionally, you can trigger the same workflow from multiple input sources (e.g., local audio files, Google Drive links, or Telegram).

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - Get a file

Type / Role: n8n-nodes-base.telegram - telegram
Config choices: Version 1.2

Block 2 - Wait

Type / Role: n8n-nodes-base.wait - wait
Config choices: Version 1.1

Block 3 - If

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 4 - Sticky Note

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 5 - Sticky Note2

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 6 - Sticky Note3

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 7 - Sticky Note5

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 8 - Sticky Note6

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 9 - Get Transcript

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 10 - Upload Audio to Assembly AI

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 11 - Route: Text vs Audio

Type / Role: n8n-nodes-base.switch - switch
Config choices: Version 3.2

Block 12 - Transcript Analysis (AI)

Type / Role: @n8n/n8n-nodes-langchain.openAi - openAi
Config choices: Version 1.8

Block 13 - Send Analysis Email

Type / Role: n8n-nodes-base.gmail - gmail
Config choices: Version 2.1

Block 14 - The End

Type / Role: n8n-nodes-base.noOp - noOp
Config choices: Version 1

Block 15 - Request Transcript from AssemblyAI2

Type / Role: n8n-nodes-base.httpRequest - httpRequest
Config choices: Version 4.2

Block 16 - Voice Message

Type / Role: n8n-nodes-base.telegramTrigger - telegramTrigger
Config choices: Version 1.2

Block 17 - Sticky Note1

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

3. Summary Table

Workflow	Transcribe & analyze Telegram voice messages with AssemblyAI & GPT-4.1 to Gmail
Complexity	advanced
Nodes	17
Categories	AI Summarization
Author	Sridevi Edupuganti
Published	15 Sept 2025

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/8605/8605.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source AI Summarization workflows

Frequently asked questions

What does Transcribe & analyze Telegram voice messages with AssemblyAI & GPT-4.1 to Gmail do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your AI Summarization use case.

Sridevi Edupuganti

10 workflows

Nodes

n8n-nodes-base.telegram n8n-nodes-base.wait n8n-nodes-base.if n8n-nodes-base.stickynote n8n-nodes-base.httprequest n8n-nodes-base.switch @n8n/n8n-nodes-langchain.openai n8n-nodes-base.gmail

Complexity

advanced

Published 15 Sept 2025

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/8605/8605.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Build self-improving agent skills with cognee

## Quick overview A self-improving loop for agent skills, powered by the cognee Verified Node. When a skill's review scores below your threshold, it proposes a rewrite, and you approve the before/after diff before it's applied. No code required. ## How it works 1. Execute your workflow. 2. Set the demo inputs (skill name, dataset name, skill procedure markdown, review task text, and the score threshold). 3. Ingest the skill into cognee. 4. Cognee reviews the skill’s performance and returns a JSON with a score and gaps. 5. If the score is below the threshold, the workflow requests a cognee improvement proposal for the skill. 6. The workflow retrieves the full proposal from cognee and builds a human-readable before/after diff. 7. If the proposal is approved, the workflow applies the improvement in cognee, fetches the updated skill, and outputs the updated procedure and diff. ## Setup 1. Create a cognee API credential in n8n and use it in all cognee nodes (Ingest Skill, Review Skill, Propose Improvement, Get Proposal, Apply Improvement, Get Skill). Information for the credential (URL and API key) can be found in your Cognee Cloud account. 2. Update the skill parameters (skill_name, dataset_name, skill_markdown, task_text, score_threshold, and approved) to match your use case. 3. Ensure the referenced cognee dataset name exists so the skill can be stored and retrieved consistently.

View

Generate monthly BigQuery KPI PDF reports with Claude, Google Docs, Outlook and Teams

## Quick overview This workflow runs monthly to query KPI data from Google BigQuery, generates a narrative with Anthropic Claude, fills a Google Docs report template, exports it as a PDF, archives it to OneDrive, emails it via Microsoft Outlook, and posts a summary to Microsoft Teams. ## How it works 1. A schedule trigger fires on the 1st of every month at 07:00 and calculates the start and end dates of the previous full calendar month. 2. Four parallel BigQuery queries fetch revenue KPIs, top product categories, weekly sales trend, and top customers for that period. Each result set is tagged with a source label before merging. 3. All tagged rows are combined and aggregated into a single structured report payload containing KPI summaries, ranked tables, and company metadata. 4. The payload is split across two concurrent branches: one sends it to a Claude Sonnet LLM chain to generate an executive narrative with five sections (summary, revenue analysis, category insights, customer insights, and recommendation), and the other creates a named copy of a Google Docs template in your reports folder. 5. Once both branches complete, the narrative is merged into the report payload and the replacement requests for all template placeholders are constructed. 6. The Google Docs node applies all replacements in a single batchUpdate call, then the file is exported as a PDF via Google Drive. 7. The finished PDF is archived to OneDrive, emailed via Outlook with the report attached, and a formatted KPI summary card is posted to a Microsoft Teams channel. ## Setup 1. Set the following n8n environment variables before activating: GCP_PROJECT_ID, BQ_DATASET, GDOCS_TEMPLATE_FILE_ID, GDRIVE_REPORTS_FOLDER_ID, ONEDRIVE_REPORTS_FOLDER_ID, REPORT_RECIPIENTS, TEAMS_TEAM_ID, and TEAMS_CHANNEL_ID. 2. Connect a Google BigQuery credential and update the four SQL queries to match your dataset, table name, and column names. 3. Connect an Anthropic API credential to the Claude Chat Model sub-node, then manually wire its output to the ai_languageModel input (bottom connector) of the Create AI Narrative with Claude node on the canvas. 4. Connect Google Drive and Google Docs OAuth2 credentials. In Google Drive, create a master report template Doc containing the placeholder strings listed in the Customization section, note its file ID from the URL, and set GDOCS_TEMPLATE_FILE_ID accordingly. 5. Connect Microsoft OneDrive, Outlook, and Teams OAuth2 credentials. Retrieve your Teams team ID and channel ID using the Microsoft Graph Explorer and set the corresponding environment variables. ## Requirements - Google Cloud project with BigQuery enabled and an orders table matching the SQL schema in the workflow - Google Workspace account (Drive and Docs OAuth2 access) - Anthropic API key - Microsoft 365 account with OneDrive, Outlook, and Teams access ## Customization - To change the reporting cadence, update the cron expression in the schedule trigger: 0 7 * * 1 for weekly or 0 7 * * * for daily. - To adapt the SQL queries to your schema, replace orders, order_total, customer_id, is_new_customer, created_at, and product_category with your actual column names. - To change the AI model, update the model field in the Claude Chat Model sub-node. - To add more KPI sections, extend the SQL queries, the aggregation code in Consolidate BigQuery Data, and the replacements array in Construct Replacement Requests.

View

Monitor multi-city courier weather risk with Open-Meteo, GPT-4o, Gemini and Slack

## Quick overview This workflow checks 48-hour forecasts from Open-Meteo for multiple cities on a 6-hour schedule or via an on-demand n8n form, scores conditions against courier-impact thresholds, uses OpenAI (with Google Gemini fallback) to draft Slack-ready alerts, and posts operational updates to a Slack channel. ## How it works 1. Runs every 6 hours on a schedule or starts from an Operations Manager on-demand n8n form submission. 2. Builds a city configuration (all cities for scheduled runs, or a single selected city for on-demand runs) and constructs the Open-Meteo forecast API request. 3. Fetches a 48-hour hourly forecast from Open-Meteo and continues even if the request fails. 4. Scores each city’s forecast against rain, wind, snow, and heat thresholds across multiple time windows, applies 18-hour deduplication for scheduled runs, and flags any city feed failures. 5. Sends the alert candidates to OpenAI to generate a three-sentence, operations-focused message per city (using Google Gemini as the model fallback if configured). 6. Formats each alert as a Slack Block Kit message and posts it to the #ops-weather-alerts channel, and separately posts a Slack error notice if one or more city forecasts could not be fetched. ## Setup 1. Add an OpenAI API credential (used to write the Slack alert messages). 2. Add a Google Gemini (PaLM) API credential if you want the configured fallback model to be available. 3. Add a Slack OAuth2 credential and set or create the target channel (ops-weather-alerts / #ops-weather-alerts) in your Slack workspace. 4. For on-demand checks, share the n8n form URL with your team and update the city dropdown options and the city configuration code if you add or rename cities. 5. Review and adjust the per-city weather thresholds in the city configuration to match your courier operations risk tolerance. ## Requirements - OpenAI API key (GPT-4o / gpt-4o-mini) - Slack OAuth2 credential with chat:write scope - Google Gemini API key (optional, for AI fallback) ## Customization - Add or remove cities by editing the CITIES array in the City config node, no other nodes need to change. - Adjust URGENT/HEADS_UP score thresholds in the Score + dedup node to raise or lower sensitivity per city. - Change the delivery peak windows (default 11:00-14:00 and 17:00-22:00) in the same node to match your market hours. - Swap the Slack channel name in both Slack nodes to route alerts to a different channel. ## Additional info This workflow was built and tested on a self-hosted n8n instance (Oracle Cloud A1 Flex, Ubuntu 24.04) and is fully compatible with n8n Cloud. Weather data is sourced exclusively from Open-Meteo (open-meteo.com), an open-source weather API requiring no authentication. Forecast accuracy follows Open-Meteo's standard model ensemble — verify critical alerts against local meteorological services before operational decisions. Deduplication uses n8n workflow static data (global scope). Clearing static data manually or migrating the workflow to a new instance will reset the deduplication state, causing the next scheduled run to re-evaluate all cities as if no prior alerts have been sent. The GPT-4o prompt includes city-relative climate context so the model understands that an alert in Nairobi means sustained flooding rain, while an alert in Helsinki means genuinely exceptional conditions beyond the Nordic baseline. This prevents generic alert copy across climatically different markets. The form trigger is designed for Operations Managers with no technical background — no n8n access required. Share the webhook URL directly and they can force an immediate check from any browser. Peak delivery windows (11:00-14:00 and 17:00-22:00 local time) are used to escalate severity scoring during high-order-volume periods. Adjust these in the Score + dedup node to match your market's actual peak hours.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

Transcribe & analyze Telegram voice messages with AssemblyAI & GPT-4.1 to Gmail

Workflow preview

Important notice

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

Telegram Voice → AI Summary & Sentiment Analysis via Gmail

Use cases

How it works

How to use

Requirements

Customising this workflow

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - Get a file

Block 2 - Wait

Block 3 - If

Block 4 - Sticky Note

Block 5 - Sticky Note2

Block 6 - Sticky Note3

Block 7 - Sticky Note5

Block 8 - Sticky Note6

Block 9 - Get Transcript

Block 10 - Upload Audio to Assembly AI

Block 11 - Route: Text vs Audio

Block 12 - Transcript Analysis (AI)

Block 13 - Send Analysis Email

Block 14 - The End

Block 15 - Request Transcript from AssemblyAI2

Block 16 - Voice Message

Block 17 - Sticky Note1

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions