Resources · Make integration

Google Cloud Text-to-Speech Make integrationAutomate Google Cloud Text-to-Speech with Make.

What if every piece of text your tools produce could come back as a voice? The Google Cloud Text-to-Speech Make integration gives you 2 action modules and no trigger. This guide is for teams who want spoken audio without code, and it walks you from connection to a working first scenario.

Try the Google Cloud Text-to-Speech integration on MakeSee the 2 modules

Verified Trustpilot reviews · AI, automation & growth agency

What you can automate

What does the Google Cloud Text-to-Speech Make integration do?

The Google Cloud Text-to-Speech Make integration lets a Make scenario, the automation you build as a chain of bricks called modules, send text or SSML (text tagged with voice instructions) to Google and get a spoken version back. You decide where the text comes from and where the result goes, without writing a line of code.

A voice for your content. A new article or product description lands in your content tool; another app's module starts the scenario and Synthesize a Speech turns that text into speech you can pass to the next step.

Spoken messages from structured data. A row added to a table, for example through the Airtable Make integration, can feed its text to Synthesize a Speech, so an operations team gets a narrated version of each record.

Anything the listed modules skip. Google's API goes further than one module. Make an API Call reaches other endpoints with the same connection, which is how you cover a need the catalog does not list.

Know the limits before you start: this app has no trigger, so something else has to launch the scenario, and the Make documentation for it is flagged as AI-generated content that you should check against Google's own docs. The same app often has an n8n node too; the n8n vs Make comparison helps you pick, and the Make training covers the editor from scratch.

Connect

How do you connect Google Cloud Text-to-Speech to Make?

  1. 01

    Prepare your Google Cloud project

    You need a Google Cloud account with billing enabled. In the Google Cloud Console, open APIs and services, then Credentials, click Create credentials and choose OAuth client ID. If asked for a callback URI, paste https://www.integromat.com/oauth/cb/google-custom.

  2. 02

    Copy the Client ID and Client secret

    Click Create and Google shows two values on screen: the Client ID and the Client secret. Copy both somewhere safe for a moment, because Make asks for them in the next step.

  3. 03

    Create the connection in Make

    Add a Google Cloud Text-to-Speech module to your scenario and click Create a connection. A connection is your Google account linked to Make once and reused by both modules. Name it in Connection name if you like, paste the credentials, then follow the on-screen prompts.

First scenario

Your first scenario with Google Cloud Text-to-Speech

GoalWhen new text shows up in one of your apps, Make sends it to Google Cloud Text-to-Speech and gets a spoken version back.

  1. 01

    Create the scenario

    From the Scenarios page, create a new scenario and click the +. Since this app has no trigger, pick a module from the app where your text lives, such as a new row or a new record.

  2. 02

    Add Synthesize a Speech

    Click the + to the right of that first module, search for Google Cloud Text-to-Speech and pick Synthesize a Speech. Select your connection, or click Create a connection if this is your first time.

  3. 03

    Map the text

    Fill the module with the text or SSML to voice, mapping it from the first module. Each bundle, one item passed between modules like one row, then becomes one request to Google.

  4. 04

    Test with Run once

    Click Run once. Make runs the scenario a single time and shows the bundles each module received, so you can confirm Google returned speech before going further.

  5. 05

    Schedule and switch on

    Open the clock on the first module to set the schedule, which is every 15 minutes by default, then switch the scenario on. Each module run on a bundle counts as one operation on your Make plan.

Modules

What the Google Cloud Text-to-Speech modules do

Google Cloud Text-to-Speech gives you 2 modules. For each one: what it does for you, when to reach for it, and what to watch out for.

Google Cloud Text-to-Speech1

Make an API Call

Action

In Make“Performs an arbitrary authorized API call.”

Opens the rest of Google's Text-to-Speech API to your scenario, reusing the connection you already created, so you are not stuck with a single listed module.

When to use it
you need an endpoint of the API that Synthesize a Speech does not cover, and you are comfortable reading Google's API reference.
Watch out
Make builds nothing for you here, so the request must match Google's documentation exactly.
Google Cloud Text-to-Speech2

Synthesize a Speech

Action

In Make“Synthesizes a speech by text or SSML.”

Gives you spoken audio from the text or SSML you send, which is the heart of this integration and the module most scenarios will use.

When to use it
a new description, message or note arrives from another app and you want a voiced version of it without leaving Make.
Watch out
every bundle that reaches it is a separate request to Google and a separate operation in Make, so filter the text upstream.
Need help

Need help automating Google Cloud Text-to-Speech with Make?

A person reads every message.

FAQ

Questions about the Google Cloud Text-to-Speech Make integration

01Is the Google Cloud Text-to-Speech Make integration free?
Yes on the Make side: it is a standard app, available from the Free plan. That plan allows 2 active scenarios, at least 15 minutes between scheduled runs, 5 minutes of execution per run, files up to 5 MB and 512 MB of data transfer. Paid plans (Core, Pro, Teams, Enterprise) drop the interval to 1 minute. Google bills its own service separately, which is why the account needs billing enabled; check Google's pricing page for that part.
02What do you need to connect Google Cloud Text-to-Speech to Make?
A Google Cloud account with billing enabled and OAuth credentials. You create an OAuth client ID under APIs and services, then Credentials, in the Google Cloud Console, adding the callback URI Make provides when prompted. Google then shows a Client ID and a Client secret, which you paste when you click Create a connection in Make. The connection is reused by both modules of the app, so you set it up only once.
03Can a Google Cloud Text-to-Speech scenario start on its own?
Not from this app: Google Cloud Text-to-Speech has no trigger module in Make, only 2 actions. The scenario therefore starts somewhere else. Either another app's trigger launches it when new text appears, or the first module runs on Make's schedule, every 15 minutes by default. You can also start with a webhook from Make. Synthesize a Speech then sits after that first step and receives the text to voice, one bundle at a time.
04What if a Google Cloud Text-to-Speech feature is missing in Make?
Use Make an API Call. It sends a request to any endpoint of Google's Text-to-Speech API with the connection you already have, so you are not limited to Synthesize a Speech. You write the request yourself, following Google's API reference for the endpoint you need. Keep in mind that Make flags its documentation for this app as AI-generated, so confirm important details in Google's own documentation before building a scenario on them.
05Make or n8n for Google Cloud Text-to-Speech?
It depends on the tool your team already runs. On Make, the app gives you Synthesize a Speech and Make an API Call, with a Run once test and scheduling on the first module. The same app often has an n8n node as well. Compare how each tool fits the rest of your stack and the skills you have in house rather than looking for a winner on this single app.
Same platform

Other docs you might need on this stack.

Browse all integrations