Hey, fam! What is your experience in this niche? Is there a demand for it in your country? Especially for voice agents. Is anyone in Europe here, who's building this? If so, which voice agents are you using? Do you connect the back end to an R-Keeper-like terminal, and is this actually necessary, or do you just enter data into an Airtable? I'm excited to read your answers!

Made this TG workflow with Message Batching for the cases when clients send more than one message within 30 seconds. LLM receives them in one string. IMPORTANT: will not work on Manychat because Manychat HTTP requests timeout after 10 seconds. But if you use META App approach, it will def work for Instagram, Whatsapp and FB messages It uses two Google Sheets: - Message Retention (date | user_id | message) — queues incoming messages. - Message Checkup (user_id | is_waiting | last_updated) — debounces per user. Flow per message: 1. Log to Message Retention. 2. Read Message Checkup for that user_id. If empty, synthesize { is_waiting:false }. 3. IF (OR):last_updated is older than 30s, oris_waiting is false→ Start wait window: set is_waiting=true, update last_updated, Wait (e.g., 30s). 4. After Wait: fetch all queued messages for the user, merge them, delete those rows, send one AI answer to Telegram, then clear the Waiting row. 5. If a new message arrives while waiting, we only refresh last_updated (extend the window) — we do not start another wait. Copy/paste: - Older-than-30s: {{ new Date(Date.now() - 30000).toISOString() }} - “No Rows” normalizer (Code node) ensures the IF always has data to check. Supports text and voice (voice via Whisper). Works reliably on Telegram once the webhook is registered and Sheets are shared with the service account.

Question for you: how much would you pay for an app with even cooler functions if you could use your own API key and only pay for API calls to Whisper, which is cheap? Would you prefer to pay monthly or in one go? What would be an adequate price?

UPDATE: I managed that through aggregating the messages in two separate Google Sheets, that's working. BUT - only for Telegram. The Bummer is: if Instagram is connected via Manychat, it's not gonna work. Manychat timeouts HTTP requests that take longer than 10s. So any external delay means failing automation... For those using n8n with Instagram or WhatsApp chatbots, how do you handle message aggregation? For example, if a user sends three separate messages that are actually part of one query: Hi Quick question What's the pricing? Without any processing, n8n would trigger three separate webhooks. How do you ensure that these get consolidated into a single message before passing it on to the chatbot workflow? - Do you rely on external tools for this? - Or do you build a buffer automation in n8n that waits (e.g. 10–20 seconds) to capture multiple messages within that window and then merge them? Curious to hear how others approach this—thanks!

Hey all, anyone uses GHL when working with multiple clients? It def integrates well wit n8n, but I'd like to hear about particular use cases from you :-) Any success stories? The platform seems to have everything in one package (even chatbots and voice agents, but I havent tested their quality yet). My idea is to simplify client management and onboarding and also leverage the AI functionality, and I'm looking for a CRM that would be applicable to any client.