Skip to content

Every 15 minutes

Transcribe emailed audio and save summaries to Drive

Voice notes and recordings sent to your inbox become a transcript and summary in Drive, with the summary emailed to you.

Runs
Every 15 minutes
Apps
Gmail, Google Drive
AI
Yes, uses the built-in AI allowance
Access
Gmail gmail.modify; Drive write

Send this to your assistant

Create a ClickRuntime automation: when an email with an audio attachment arrives, transcribe it, write a summary, save both to my Drive 'Transcripts' folder and email me the summary.

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 consultant records client calls on her phone and emails the files to herself. They pile up in her inbox, and when she needs to recall what a client agreed, she has to listen to forty minutes of audio to find one sentence.

Turning each recording into a searchable transcript and a short summary means the key points are in writing the same day and the full text is there when details matter.

What you get out of it

  • Find what was said in seconds

    Transcripts in Drive can be searched like any document, so a figure or promise from a call is a quick search away.

  • Follow-ups written while fresh

    The summary arrives soon after the recording, which makes it easy to send a recap or action list to the client the same day.

  • Recordings kept in one place

    Every transcript sits in one Drive folder instead of scattered across email threads and phone storage.

  • Works with any recorder

    Any app or device that can email an audio file works, so there is nothing new to install on your phone.

How it works

What happens, step by step

  1. Every few minutes ClickRuntime checks your Gmail for new emails with an audio attachment.

  2. It skips any email it has already handled.

  3. The audio is transcribed, and AI writes a short summary with the main points and any action items.

  4. The transcript and summary are saved to your Transcripts folder in Google Drive, and the summary is emailed to you.

Before it runs live

  • Connect Google through your own Google app (a one-time, 10-minute setup), so it works with your own Gmail
  • Connect Google Drive

What you get

RunsEvery 15 minutes
Transcribe emailed audio and save summaries to Drivetoday, 9:00Succeeded
Email · Call summarySummary: acme-kickoff.m4a. Acme agreed to a June launch; we send the revised quote by Friday.

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 Gmail and Google Drive 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.
audio_files_transcribed_and_summaries_saved_to_drive.pyexample
import base64
from googleapiclient.discovery import build
from google.oauth2.credentials import Credentials
from clickruntime import on_trigger, credentials, notify, ai, report_fetched, http

FOLDER = "transcripts-folder-id"

@on_trigger
def run(event):
    creds = Credentials(credentials.connection("google", "work"))
    gmail = build("gmail", "v1", credentials=creds, cache_discovery=False).users()
    msgs = gmail.messages().list(userId="me", q="has:attachment filename:(mp3 OR m4a OR wav) -label:transcribed newer_than:1d").execute().get("messages", [])
    report_fetched(len(msgs))
    if not msgs:
        return {"summary": "No new audio"}
    for m in msgs:
        part = next(p for p in gmail.messages().get(userId="me", id=m["id"]).execute()["payload"]["parts"] if p.get("filename"))
        data = gmail.messages().attachments().get(userId="me", messageId=m["id"], id=part["body"]["attachmentId"]).execute()["data"]
        text = http.post("https://api.openai.com/v1/audio/transcriptions", headers={"Authorization": f"Bearer {credentials.secret('OPENAI_API_KEY')}"},
                         files={"file": (part["filename"], base64.urlsafe_b64decode(data))}, data={"model": "whisper-1"}).json()["text"]
        summary = ai.generate(f"Summarise with action items:\n{text[:20000]}", max_output_tokens=400).text
        http.post("https://www.googleapis.com/upload/drive/v3/files?uploadType=multipart", headers={"Authorization": f"Bearer {creds.token}"},
                  files={"metadata": (None, f'{{"name": "{part["filename"]}.txt", "parents": ["{FOLDER}"]}}', "application/json"),
                         "file": ("t.txt", f"SUMMARY\n{summary}\n\nTRANSCRIPT\n{text}", "text/plain")})
        notify.email_me(f"Summary: {part['filename']}", summary)
    return {"transcribed": len(msgs)}

FAQ

Common questions

Which audio formats are supported?
Common formats such as MP3, M4A and WAV. Very long recordings may be split into parts, and each part is transcribed in turn.
Can it tell speakers apart?
Speaker labels depend on the transcription service used. Without them, the transcript is one block of text and the summary still lists the main points.
Does it only look at emails from me?
You can limit it to emails from your own address or with a word in the subject, so audio from newsletters or other senders is ignored.
What permissions does it need?
Gmail gmail.modify; 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 each time it checks. Checks that find nothing new and stop right away aren't counted.
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 emailed audio and save summaries to Drive” from your assistant

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