The moment it happens

Transcribe a recording with speaker labels

Send a link to an interview or call and get back the text, split by speaker, by email.

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

Send this to your assistant

Create a ClickRuntime automation: give me a link I can send audio URLs to. Transcribe each recording with AssemblyAI using speaker labels and email me the full text.

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 podcast producer, a researcher with interview recordings or a sales manager with call recordings all share a problem: audio holds useful content that nobody has time to listen to again. Transcribing by hand takes about four hours for each hour of audio, and uploading files to a transcription tool means logging in, waiting and downloading. Without a transcript, you cannot search a conversation for a quote or share it with a colleague who missed it.

Send an audio file URL to your ClickRuntime link. ClickRuntime submits it to AssemblyAI with speaker labels turned on, waits for the transcript to finish and emails you the full text with each speaker marked. You do not need to open any transcription tool.

It suits anyone with recordings stored online, such as in a cloud drive or a call platform that exposes download links.

What you get out of it

Recordings become searchable text
Once a conversation is written down, you can search for a customer's exact wording or a decision from last month. Audio you never reopened becomes a resource you actually use.
Speaker labels save manual editing
Knowing who said what turns a wall of text into a readable dialogue. Interviews and calls make sense without replaying the audio to work out which voice was whose. You never replay audio to settle who spoke.
No tool to log into
Sending a link and receiving an email replaces a login, an upload and a download. That means colleagues who have never used a transcription service can still get transcripts. Anyone can request one from a phone.
Quotes and action items can be pulled fast
A journalist or product manager can find a quote in a minute and paste it into a document. Reviewing a one-hour call no longer means scrubbing back and forth through audio.
Transcripts can be shared with people who missed it
Forwarding an email with the full text lets absent teammates catch up in ten minutes of reading, rather than an hour of listening. Absent colleagues read for ten minutes, not an hour.

How it works

What happens, step by step

When you send a link to a recording to your personal ClickRuntime link, the automation starts straight away.
ClickRuntime sends the recording to AssemblyAI and asks it to label each speaker.
It waits until the transcript is ready.
You get an email with the text split by speaker, or the error if transcription failed.

Before it runs live

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

What you get

RunsThe moment it happens

Transcribe a recording with speaker labelsjust nowSucceeded

Email · TranscriptsSpeaker A: Thanks for joining, let's start with the Northwind rollout. Speaker B: Sure, we're on track for November.

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 AssemblyAI 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_posted_to_a_link.pyexample

import time
from clickruntime import on_event, credentials, notify, http

API = "https://api.assemblyai.com/v2/transcript"

@on_event
def handle(event):
    url = (event.json or {})["url"]
    headers = {"authorization": credentials.secret("ASSEMBLYAI_API_KEY")}
    t = http.post(API, headers=headers, json={"audio_url": url, "speaker_labels": True}).json()
    while t["status"] not in ("completed", "error"):
        time.sleep(5)
        t = http.get(f"{API}/{t['id']}", headers=headers).json()
    if t["status"] == "error":
        notify.email_me("Transcription failed", f"{url}\n{t['error']}")
        return {"status": "error"}
    text = "\n".join(f"Speaker {u['speaker']}: {u['text']}" for u in t["utterances"])
    notify.email_me("Transcript ready", f"{url}\n\n{text}")
    return {"utterances": len(t["utterances"])}

FAQ

Common questions

What audio formats and lengths are supported?

AssemblyAI accepts common formats such as MP3, WAV, M4A and many video containers, as long as the URL is reachable. Long recordings work too, though processing takes longer. Files that need a login to open must be shared with a link that works without signing in.

How long does it take to get the email?

Transcription generally takes a fraction of the audio's length, so an hour of audio is often done in a few minutes. ClickRuntime checks the job status until it finishes, then emails the text, so the wait depends mostly on file size.

Does it work with several speakers or just two?

Speaker labels identify different voices and tag them as Speaker A, Speaker B and so on. It works for panels as well as two-person calls, though accuracy drops when voices overlap heavily or the recording is noisy.

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