The moment it happens

Email yourself a transcript of any recording

Send a link to an audio file and the transcript, with a short summary, arrives in your inbox.

Runs: The moment it happens
Apps: Deepgram
AI: Not needed
Access: Member key

Send this to your assistant

Create a ClickRuntime automation: give me a link I can send audio URLs to. Transcribe each one with Deepgram, include Deepgram's summary, and email me both.

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 recruiter finishes a screening call recorded in a cloud folder and wants the conversation in text before the debrief. A journalist has an interview to quote from. A founder has a voice memo of ideas. Each ends up uploading the file to a transcription site, waiting, copying the result and pasting it into an email, which takes ten minutes of attention per recording and gets skipped when the week is busy.

Send the automation a link to an audio file and it calls Deepgram's speech-to-text with summarization turned on, then emails you the full transcript and a short summary of the conversation in one message. It runs when the link arrives, so the email is usually in your inbox by the time the recording would have finished uploading somewhere else.

It suits anyone who handles a steady trickle of recordings and wants text without opening another tool.

What you get out of it

Searchable text instead of audio
A transcript can be searched for a name, a price or a commitment. An hour-long recording that nobody replays becomes something you can find an answer in within seconds, and quotes can be copied exactly instead of paraphrased from memory.
A summary to decide whether to read
The short summary tells you whether the call needs your full attention. That lets you triage ten recordings in the time it takes to listen to one, which matters when the useful part was buried after a long tangent.
No file juggling between tools
You send a URL once. There is no download, upload or copy-and-paste step in which a file can be misplaced or a transcript pasted under the wrong email thread, and the email itself becomes the record, so there is nothing to file by hand.
Consistent notes after every call
When transcripts land in the same place in the same shape every time, a team can rely on them for follow-ups, hand-offs and quoting, instead of each person's patchy memory. Over a quarter, that consistency is worth more than any single transcript.
Cheap to run on demand
You only pay for audio you actually send. There is no standing subscription to a separate transcription product that you use twice a month, so the cost stays proportional to use, which suits irregular workloads such as seasonal hiring or interview series.

How it works

What happens, step by step

When you send a link to an audio file to your personal ClickRuntime link, the automation starts straight away.
Deepgram transcribes the recording and writes a short summary.
You get an email with the file link, the summary and the full transcript.

Before it runs live

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

What you get

RunsThe moment it happens

Email yourself a transcript of any recordingjust nowSucceeded

Email · TranscriptsSummary: The team agreed to move the Northwind launch to November and hire one more support agent.

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 Deepgram 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_and_email_the_transcript.pyexample

from clickruntime import on_event, credentials, notify, http

@on_event
def handle(event):
    url = (event.json or {})["url"]
    resp = http.post("https://api.deepgram.com/v1/listen",
                     params={"summarize": "v2", "smart_format": "true", "model": "nova-3"},
                     headers={"Authorization": f"Token {credentials.secret('DEEPGRAM_API_KEY')}"},
                     json={"url": url}, timeout=300)
    resp.raise_for_status()
    results = resp.json()["results"]
    transcript = results["channels"][0]["alternatives"][0]["transcript"]
    summary = (results.get("summary") or {}).get("short", "")
    notify.email_me("Transcript ready", f"{url}\n\nSummary:\n{summary}\n\nTranscript:\n{transcript}")
    return {"chars": len(transcript)}

FAQ

Common questions

What kind of audio link does it accept?

It needs a URL that Deepgram can fetch directly, such as a public or pre-signed link to an MP3, WAV or M4A file. A page that merely embeds a player, or a link behind a login, will not work. Test the link in a private browser window before you send it.

Does it handle more than one speaker?

Deepgram can label speakers when diarization is enabled, which marks who is talking in the transcript. Without it, everything is attributed to a single stream of text. Tell your AI assistant to turn it on if you transcribe meetings or interviews with multiple voices.

How long does it take for the email to arrive?

Deepgram transcribes much faster than real time, so a typical recording comes back within a minute or two. Very long files take longer. The run log in the ClickRuntime dashboard shows whether the transcription call is still in progress or has finished and been emailed.

What permissions does it need?

Member 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.

Daily