Skip to content

The moment it happens

Transcribe voice notes sent to Telegram and save them to Drive

Send a voice note or audio file to your Telegram bot and get the text and a summary back, with both saved to your Transcripts folder.

Runs
The moment it happens
Apps
Google Drive, Telegram
AI
Yes, uses the built-in AI allowance
Access
Telegram bot token; Drive write

Send this to your assistant

Create a ClickRuntime automation: when I send audio to my Telegram bot, transcribe it, reply with the text and a short summary, and save both to my Drive 'Transcripts' folder.

Paste it into your assistant. It tells you what it will send or change before it runs live.

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A site manager thinks best while driving between jobs. He records voice notes about what he saw, what needs ordering and who to call, but listening back to find one detail takes longer than it took to say. Notes recorded on his phone never make it to the office.

Turning each voice note into text and a short summary, and filing both in Drive, makes spoken notes as easy to search and share as typed ones. Field workers, writers, founders and anyone who prefers talking to typing use it to capture ideas on the move.

What you get out of it

  • Speak now, read later

    Record your thoughts whenever it suits you, and get searchable text back within a minute or two.

  • A summary for long recordings

    A few lines with the main points saves reading the full transcript when you only need the gist.

  • Everything filed in one place

    Transcripts and summaries are saved to Drive, where colleagues can read them and search finds them later.

  • Works from any phone

    Telegram is all you need. There is no extra app to install or recorder to carry.

How it works

What happens, step by step

  1. ClickRuntime starts as soon as you send a voice note or audio file to your Telegram bot.

  2. It ignores messages from chats you have not allowed and any message it has already handled.

  3. The audio is transcribed, and AI writes a short summary of the main points.

  4. You get the text and summary as a reply in Telegram, and both are saved as a document in your Drive Transcripts folder.

Before it runs live

  • Connect Google Drive
  • Connect Telegram
  • Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens
Transcribe voice notes sent to Telegram and save them to Drivejust nowSucceeded
Telegram · Voice notesSummary: order 40 sheets of plasterboard for the Acme Road job; call the electrician about Thursday; client wants a second quote for the kitchen.

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.
  • 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 Google Drive and Telegram steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.
transcribe_audio_sent_to_telegram_store_in_drive.pyexample
import io
from google.oauth2.credentials import Credentials
from googleapiclient.discovery import build
from googleapiclient.http import MediaIoBaseUpload
from clickruntime import on_event, credentials, http, state, ai

FOLDER_ID, ALLOWED_CHAT = "your-transcripts-folder-id", 123456789

@on_event
def handle(event):
    msg = (event.json or {}).get("message", {})
    audio = msg.get("voice") or msg.get("audio")
    if not audio or msg["chat"]["id"] != ALLOWED_CHAT or state.get(f"done:{event.event_id}"):
        return {"skipped": True}
    tg = f"https://api.telegram.org/bot{credentials.secret('TELEGRAM_BOT_TOKEN')}"
    path = http.get(f"{tg}/getFile", params={"file_id": audio["file_id"]}).json()["result"]["file_path"]
    data = http.get(f"https://api.telegram.org/file/bot{credentials.secret('TELEGRAM_BOT_TOKEN')}/{path}").content
    text = http.post("https://api.openai.com/v1/audio/transcriptions", headers={"Authorization": f"Bearer {credentials.secret('OPENAI_API_KEY')}"},
                     files={"file": ("audio.ogg", data)}, data={"model": "whisper-1"}).json()["text"]
    summary = ai.generate(f"Summarise this voice note in 3 bullet points:\n{text[:12000]}", max_output_tokens=250).text
    http.post(f"{tg}/sendMessage", json={"chat_id": ALLOWED_CHAT, "text": f"Summary:\n{summary}\n\nTranscript:\n{text[:3500]}"})
    drive = build("drive", "v3", credentials=Credentials(credentials.connection("google", "work")), cache_discovery=False)
    drive.files().create(body={"name": f"Voice note {event.received_at[:16]}", "parents": [FOLDER_ID], "mimeType": "application/vnd.google-apps.document"},
                         media_body=MediaIoBaseUpload(io.BytesIO(f"Summary\n{summary}\n\nTranscript\n{text}".encode()), mimetype="text/plain")).execute()
    state.set(f"done:{event.event_id}", True)
    return {"chars": len(text)}

FAQ

Common questions

What audio can I send?
Telegram voice notes and audio files such as MP3 or M4A. Recordings of several minutes work well.
Which languages are supported?
Most widely spoken languages. The transcript is in the language you spoke, and the summary can be in the same language or another one you choose.
Who can send audio to the bot?
Only the chats you allow. Messages from anyone else are ignored, so a stranger who finds your bot cannot fill your Drive.
What permissions does it need?
Telegram bot token; Drive write. Nothing else in your accounts is used.
Does it need AI?
Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.
How many runs does it use?
One run for each event the app sends.
Can I change how it works?
Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

Set up “Transcribe voice notes sent to Telegram and save them to Drive” from your assistant

Copy the prompt above, or connect your assistant first. Free plan, no credit card.