The moment it happens
Turn a voice note on Telegram into a LinkedIn post
Send a rough idea or voice note to your bot, get a polished LinkedIn post back, and publish it when you confirm.
- Runs
- The moment it happens
- Apps
- LinkedIn, Telegram
- AI
- Yes, uses the built-in AI allowance
- Access
- bot token; LinkedIn w_member_social
Send this to your assistant
Create a ClickRuntime automation: when I send a message or voice note to my Telegram bot, transcribe it if needed, turn it into a polished LinkedIn post, send it back for me to confirm, and publish it to LinkedIn when I tap Post.
First time? Adding ClickRuntime to your assistant takes about two minutes.
Why use it
Why teams use this automation
A business owner thinks best out loud, on walks or in the car, and has plenty to say on LinkedIn. Sitting down to type it up is where the ideas die.
Now they record a voice note to a Telegram bot. A clean, well-structured LinkedIn post comes back in their own words, and one tap publishes it.
What you get out of it
Speak, don't type
A rambling voice note becomes a tidy post.
Still sounds like you
Your words and examples are kept, just organised.
Confirm before posting
Nothing goes out until you tap Post.
Works on the move
Record anywhere, publish from your phone.
How it works
What happens, step by step
You send a text or voice note to your Telegram bot.
A voice note is transcribed, and AI turns your words into a LinkedIn post.
The draft is saved and sent back to you with a Post button.
When you tap Post, it's published to LinkedIn and the bot sends you the link.
Before it runs live
- Connect LinkedIn
- Connect Telegram
- Paste your automation's link into the other app's webhook settings
What you get
Build your own
Need it to work differently?
Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.
Changes you can ask for
- Act only on the items that match your own rules, and skip the rest
- Change what the AI looks for, or how it writes the result
- Add another app, for example also send it to Slack
- Combine it with other LinkedIn and Telegram steps into one automation
Under the hood
The code that runs this automation
from clickruntime import on_event, credentials, http, ai, state
AUTHOR = "urn:li:person:abc123"
@on_event
def handle(event):
body, token = event.json or {}, credentials.secret("TELEGRAM_BOT_TOKEN")
tg = f"https://api.telegram.org/bot{token}"
if (cb := body.get("callback_query")) and (d := state.get("draft")):
r = http.post("https://api.linkedin.com/rest/posts", headers={"Authorization": f"Bearer {credentials.connection('linkedin', 'work')}", "LinkedIn-Version": "202409"},
json={"author": AUTHOR, "commentary": d["text"], "visibility": "PUBLIC", "lifecycleState": "PUBLISHED", "distribution": {"feedDistribution": "MAIN_FEED"}})
http.post(f"{tg}/sendMessage", json={"chat_id": d["chat"], "text": f"Live: https://www.linkedin.com/feed/update/{r.headers.get('x-restli-id')}"})
state.delete("draft")
return {"posted": True}
msg = body.get("message", {})
words = msg.get("text", "")
if msg.get("voice"):
path = http.get(f"{tg}/getFile", params={"file_id": msg["voice"]["file_id"]}).json()["result"]["file_path"]
audio = http.get(f"https://api.telegram.org/file/bot{token}/{path}").content
words = http.post("https://api.transcribe.northwind.example/v1/transcribe", data=audio,
headers={"Authorization": f"Bearer {credentials.secret('TRANSCRIBE_API_KEY')}"}).json()["text"]
text = ai.generate(f"Turn this into a clear LinkedIn post, keeping my words and examples:\n{words[:6000]}", max_output_tokens=600).text
state.set("draft", {"text": text, "chat": msg["chat"]["id"]})
http.post(f"{tg}/sendMessage", json={"chat_id": msg["chat"]["id"], "text": text,
"reply_markup": {"inline_keyboard": [[{"text": "Post", "callback_data": "post"}]]}})
return {"drafted": True}FAQ
Common questions
How long can voice notes be?
Can I edit the draft?
What languages work?
What permissions does it need?
Does it need AI?
How many runs does it use?
Can I change how it works?
Related
You might also like
Send a topic to Telegram and approve a LinkedIn draft
Send a topic to your bot, get a well-researched LinkedIn draft back, and it's posted when you tap Approve.
See how it worksSchedule AI LinkedIn posts with Telegram approval
On your schedule a LinkedIn post is written from your themes, sent to Telegram for approval, published, and confirmed.
See how it worksShare new articles on LinkedIn and get a Telegram note
New articles from your blog, Medium or Dev.to are posted to LinkedIn with a short intro, and Telegram confirms each one.
See how it worksKeep exploring
Set up “Turn a voice note on Telegram into a LinkedIn post” from your assistant
Copy the prompt above, or connect your assistant first. Free plan, no credit card.