The moment it happens

Translate recordings into English

Audio in another language comes back as an English transcript, with an optional spoken version.

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

Send this to your assistant

Create a ClickRuntime automation: when I post an audio file to my link, translate it into English, then email me the English text and an MP3 of it read aloud.

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 small export business gets voice messages from suppliers in Portuguese, Turkish or Vietnamese, and nobody in the office speaks those languages. A support lead receives recorded customer complaints in Spanish and has to find a colleague to listen. Waiting for a translator or pasting audio into free tools slows replies, and sensitive recordings end up on whatever website was convenient.

When an audio file is posted to your link, OpenAI's translation endpoint turns the speech into English text. If you want, the text is then read back with a text-to-speech voice, so you can listen instead of reading. The English text and, if enabled, the audio link are sent to you by email within a few minutes.

It is also helpful for interviews, lectures and training recordings made in another language.

What you get out of it

Faster replies to foreign-language messages
Understanding a supplier's voice message within minutes means you can answer the same day. Delays that used to span a weekend and a search for a translator disappear. That speed can win business when a competitor takes days to respond to the same message.
No dependence on a bilingual colleague
Anyone in the team can understand a recording without finding the one person who speaks the language. That removes a bottleneck and spares that colleague from constant interruptions. It also avoids the awkward exchange of asking a favor from the same person each time a foreign-language message arrives.
Customers feel heard sooner
A complaint recorded in Spanish gets read and addressed quickly, not parked until someone is free to listen. Speedy attention often decides whether an unhappy customer stays. Prompt attention shows customers that their concerns are taken seriously, even when they write or speak in another language.
Listening option for busy people
Re-voicing the English text as audio lets you hear the message while commuting or working, which suits people who prefer to listen over reading a block of text. That is helpful when your hands are busy or your eyes are on something else, and it keeps important messages from waiting.
Recordings stay in a controlled workflow
Instead of pasting audio into random websites, files go through your own secured setup with keys stored as secrets, which is easier to defend if the content is sensitive. That control reduces the chance that private conversations are stored on services you have not reviewed or agreed to.

How it works

What happens, step by step

When you send a recording to your ClickRuntime link, the automation starts straight away.
OpenAI listens to it in its original language and writes an English translation.
If you've turned it on, an OpenAI voice reads the English text aloud and the audio is saved to Google Drive.
You get an email with the English text and, if made, a link to listen.

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

Translate recordings into Englishjust nowSucceeded

Email · English translationHello, this is Acme Lisbon confirming the shipment leaves on Friday. Listen: https://drive.google.com/file/d/…/view

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.

translate_audio_into_another_language.pyexample

import json
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')}"}
    english = http.post("https://api.openai.com/v1/audio/translations", headers=headers, timeout=120,
                        data={"model": "whisper-1"},
                        files={"file": ("audio.mp3", http.get(audio_url, timeout=60).content)}).json()["text"]
    mp3 = http.post("https://api.openai.com/v1/audio/speech", headers=headers, timeout=120, json={
        "model": "tts-1", "voice": "alloy", "input": english[:4096]}).content
    # Email is text only, so the MP3 goes to Google Drive and the email carries the link.
    drive = {"Authorization": f"Bearer {credentials.connection('google', 'work')}"}
    meta = json.dumps({"name": "translation.mp3"})
    link = http.post("https://www.googleapis.com/upload/drive/v3/files",
                     params={"uploadType": "multipart", "fields": "webViewLink"}, headers=drive,
                     files={"metadata": ("m", meta, "application/json"), "file": ("f", mp3, "audio/mpeg")}).json()["webViewLink"]
    notify.email_me("English translation", f"{english}\n\nListen: {link}")
    return {"chars": len(english)}

FAQ

Common questions

Which languages can it translate from?

OpenAI's translation endpoint accepts speech in dozens of languages, including Spanish, Portuguese, French, German, Turkish, Vietnamese, Hindi and Japanese, and always produces English text. Quality varies by language and recording clarity. Quality is best for widely spoken languages and clear audio, and you should double-check names and numbers.

Can it translate into languages other than English?

The audio translation endpoint outputs English only. To get another target language, the English text can be sent to a chat model as a second step, which is a reasonable approach for languages such as French or German.

Is the original audio kept?

The audio is sent for processing and the email contains the translation, plus a link to the generated speech if enabled. If you want the original recording saved too, a step to store it can be added.

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