OpenRuna
Sign in
← Workflows

Speech Support Workflow

22 nodes · agent, lmChatGoogleGemini, telegram, openAi, memoryManager, memoryBufferWindow

Engine
n8n
Nodes
22
Trigger
scheduled/triggered
Source file
1452_Telegram_Stickynote_Automate_Triggered.json

Workflow flow

IntegrationsAgentLmChatGoogleGeminiTelegramOpenAIMemoryManagerMemoryBufferWindowSwitch@n8n/n8n-nodes-langchain.agent@n8n/n8n-nodes-langchain.lmChatGoogleGeminiSet@n8n/n8n-nodes-langchain.openAiIF+3 more
100%

Google Gemini Chat Model

@n8n/n8n-nodes-langchain.lmChatGoogleGemini

TRIGGER

Recieve Telegram Message

Telegram

Store Conversation Memory

@n8n/n8n-nodes-langchain.memoryBufferWindow

Check For Text or Voice Message

Set

If Voice Message

IF

Download Audio File

Telegram

Transcribe Audio File

@n8n/n8n-nodes-langchain.openAi

Route Flow Based on Message Content

Switch

Wipe Conversation Memory

@n8n/n8n-nodes-langchain.memoryManager

Set prompt to generate a speech based on the feedback

Set

Set prompt to provide feedback on speech

Set

Set prompt to start a new speech

Set

AI Agent

@n8n/n8n-nodes-langchain.agent

Code to remove unwanted characters from LLM response

Code

Code to split output into chunks under 4000 characters

Code

Respond to Telegram Message

Telegram

16 steps · flows top to bottom, branches left to right

Browse by integration

agentlmChatGoogleGeminitelegramopenAimemoryManagermemoryBufferWindowswitch
Browse all integrations →
Download n8n JSONDownload sanitized JSONDownload flow graph

Import into n8n

  1. Download the n8n JSON file (full or sanitized).
  2. In n8n: Workflows → Import from file.
  3. Open each node and reconnect credentials to your accounts.
  4. Test with manual execution before enabling triggers.

Sanitized JSON removes credential IDs — safer for sharing. Flow graph JSON is OpenRuna's lightweight format for diagrams and other tools, not n8n import.

View source corpus ↗

Overview

Speech Support Workflow is a free n8n workflow on OpenRuna — 22 nodes connecting agent, lmChatGoogleGemini, telegram, openAi, memoryManager, memoryBufferWindow, switch. Download the JSON, view the flow diagram, and import it into your n8n instance.

What this workflow does

Built in n8n, "Speech Support Workflow" chains 22 nodes to move data between agent, lmChatGoogleGemini, telegram, openAi, memoryManager, memoryBufferWindow, switch. 22 nodes · agent, lmChatGoogleGemini, telegram, openAi, memoryManager, memoryBufferWindow Execution begins at the scheduled/triggered trigger and flows through the 22 configured nodes. On OpenRuna you get the visual graph, the integration list, and a downloadable JSON ready to import into n8n. Use it to learn integration patterns, fork it for your own use case, or deploy it quickly after reconnecting credentials.

Use cases

  • Study how data moves from agent to lmChatGoogleGemini before building your own variant.
  • Share it with your team as a documented reference for scheduled/triggered automations in the agent stack.
  • Import "Speech Support Workflow" into n8n, reconnect credentials for agent, lmChatGoogleGemini, telegram, openAi, memoryManager, memoryBufferWindow, switch, and run the same automation in your own workspace.
  • Use it as a starting template when wiring agent, lmChatGoogleGemini, telegram, openAi, memoryManager, memoryBufferWindow, switch — adjust node parameters to your accounts and record IDs.

Example output

Imported into n8n, "Speech Support Workflow" exposes 22 configured nodes. Trigger type: scheduled/triggered. Integrations: agent, lmChatGoogleGemini, telegram, openAi, memoryManager, memoryBufferWindow, switch. Open each node after import to map credentials to your own agent and lmChatGoogleGemini accounts. Run it once in test mode to verify any branch logic (Switch/IF nodes) before enabling production triggers.

Tips by platform

Claude

Ask Claude to turn the "Speech Support Workflow" JSON into a plain-English runbook, node by node. It can flag where agent rate limits or missing retries might bite before you go live.

ChatGPT

Drop the workflow JSON or this OpenRuna page URL into ChatGPT and ask for a step-by-step runbook: triggers, branches, and which fields to customise for agent, lmChatGoogleGemini, telegram, openAi, memoryManager, memoryBufferWindow, switch. Handy for onboarding teammates new to n8n.

Cursor

In Cursor, ask Agent mode to parameterise "Speech Support Workflow" — extract agent IDs and secrets into environment variables without changing the 22-node structure.

Frequently asked questions

How do I import "Speech Support Workflow" into n8n?
Click Download n8n JSON on this page, then in n8n choose Workflows → Import from file and select the downloaded file. Reconnect credentials on each node — the export carries credential IDs from the original author's instance, not working secrets.
Which integrations does "Speech Support Workflow" use?
It uses: agent, lmChatGoogleGemini, telegram, openAi, memoryManager, memoryBufferWindow, switch. The flow diagram above shows how each service connects across the 22 nodes. Filter OpenRuna by integration to find related workflows and tools.
Can I import a sanitized export without credentials?
Yes. Use "Download sanitized JSON" to strip credential references before sharing internally. You will still add your own agent and lmChatGoogleGemini credentials in n8n after import.
What trigger type does "Speech Support Workflow" use?
Trigger type: scheduled/triggered. After import, confirm the trigger node (webhook, schedule, or app event) matches your environment, then activate the workflow when you are ready to run it.
Is "Speech Support Workflow" free to use?
OpenRuna catalogs community n8n workflows under open licenses. Check the source corpus link for the original license; commercial use may require verifying the third-party API terms for agent, lmChatGoogleGemini, telegram, openAi, memoryManager, memoryBufferWindow, switch.

Related resources