The moment it happens

Turn voice notes into text and action items

Any recording you send to your link comes back as a transcript, a short summary and a list of to-dos.

Runs: The moment it happens
Apps: OpenAI
AI: Not needed
Access: API key

Send this to your assistant

Create a ClickRuntime automation: give me a link I can send voice notes to. Transcribe each one with Whisper, summarise it in three lines, list any action items, and email me all of it.

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

Add to ChatGPT Add to Claude

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 a phone, a manager dictates voice notes while driving, and a journalist keeps interviews on an audio recorder. The recordings pile up because typing them out takes roughly four times as long as the audio itself. Details are forgotten, quotes get paraphrased from memory, and action items that were agreed in a call never get written down.

When an audio file is sent to your link from a voice memo app, a recorder or a shared folder tool, it is transcribed by OpenAI's speech-to-text model, and the transcript is then summarized into key points and action items. The full transcript and the summary arrive together in one email, usually within a few minutes.

It is also used for lectures, meeting recordings, podcast notes and voicemail.

What you get out of it

Exact words are preserved
A transcript keeps what was actually said, which matters for quotes, commitments and disputes. You are no longer relying on a memory of a call from last Tuesday. That level of accuracy protects you in negotiations and in writing up quotations for publication.
Action items are captured while fresh
The summary lists decisions and follow-ups right after the recording ends. That means a task agreed on a call reaches your inbox the same hour and not the following week.
Searchable records of conversations
Once audio is text, a keyword search in your mail finds the call where a price was mentioned. Audio files alone cannot be searched this way. A transcript also lets a colleague who missed the call understand it without listening to the whole recording.
Hours of typing are avoided
A one-hour interview takes several hours to type out by hand. Receiving a transcript in minutes lets you spend that time on analysis and writing. Even long conversations can be reviewed in a few minutes, so your attention goes to what the speakers actually decided.
Voice notes become usable documents
Dictating while walking or driving becomes a legitimate way to capture ideas, because the result lands as readable text with the main points pulled out. That turns dead time into productive time, and it means that nothing gets lost between the moment you speak and your notes.

How it works

What happens, step by step

When you send a recording to your ClickRuntime link, the automation starts straight away.
OpenAI turns the audio into a full written transcript.
AI then writes a short summary and pulls out a list of to-dos.
You get an email with the summary, the action items and the transcript.

Before it runs live

Connect OpenAI
Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens

Turn voice notes into text and action itemsjust nowSucceeded

Email · Voice note summaryCall with Northwind about the Q4 order; they want delivery moved to 3 Nov. Action items: - Confirm new date with the warehouse

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
Add an AI step, for example to summarize, sort or draft a reply
Add another app, for example also send it to Slack
Combine it with other OpenAI 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_and_summarise_audio.pyexample

from clickruntime import on_event, credentials, http, notify

@on_event
def handle(event):
    audio_url = (event.json or {}).get("audio_url")
    if not audio_url:
        return {"error": "send JSON with audio_url"}
    headers = {"Authorization": f"Bearer {credentials.secret('OPENAI_API_KEY')}"}
    audio = http.get(audio_url, timeout=60).content
    text = http.post("https://api.openai.com/v1/audio/transcriptions", headers=headers, timeout=120,
                     data={"model": "whisper-1"}, files={"file": ("note.m4a", audio)}).json()["text"]
    chat = http.post("https://api.openai.com/v1/chat/completions", headers=headers, json={
        "model": "gpt-4o-mini",
        "messages": [{"role": "system", "content": "Summarise this voice note in three lines, then list "
                      "action items as bullets under 'Action items:'."},
                     {"role": "user", "content": text[:12000]}]}).json()
    summary = chat["choices"][0]["message"]["content"]
    notify.email_me("Voice note summary", f"{summary}\n\n--- Transcript ---\n{text}")
    return {"chars": len(text)}

FAQ

Common questions

What audio formats are supported?

OpenAI's transcription accepts common formats such as MP3, MP4, M4A, WAV and WebM, up to 25 MB per file. Longer recordings need to be split or compressed before sending, which can be done in the sending tool.

How accurate is the transcript with accents or background noise?

Accuracy is generally high for clear speech and many accents, and drops with heavy noise, overlapping speakers or poor microphones. Names and technical terms may be misspelled, so check anything that you plan to quote.

Does it separate different speakers?

The standard transcription returns text without labeling who spoke. The summary can sometimes infer speakers from context, but if you need reliable speaker labels, you would need a service built for diarization. Diarization is a different kind of service, and this setup is not built for it.

What permissions does it need?

API key. Nothing else in your accounts is used.

Does it need AI?

No. It runs without AI, so it doesn't use your plan's 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.

The moment it happens