Voiceovers: ElevenLabs + Make

A small museum wants audio narration for its exhibit labels, dozens of short scripts that visitors could play on their phones. Recording a human narrator for every label is out of budget, and pasting each script into a tool one at a time is an afternoon nobody has. The scripts are written; the bottleneck is the voicing.

This build voices them. You keep a sheet of scripts, one per row, and ElevenLabs turns each into a natural voiceover that lands in a Drive folder. A list becomes a library of audio while you do something else.

We wire it in Make, the first build in our video and voice set. Claude does not speak, so the right tool here is ElevenLabs, the clearest of the voice models. Make turns a one-at-a-time task into a batch that runs itself.

What does this workflow actually do?

In one line: a script becomes a voiceover file. Make watches your sheet. When you add a row of script text, it sends it to ElevenLabs, receives the spoken audio, and uploads the file to a Drive folder. No app-hopping, no downloading, no renaming.

A few real cases, none of them the usual ones:

• The museum above, voicing a whole set of exhibit labels in an afternoon.
• A language teacher generating pronunciation clips for each week’s vocabulary.
• A hiking-app maker generating spoken trail directions from a list.
• A meditation-app creator narrating short scripts in a consistent calm voice.

Writing the scripts is the creative work, and you still do it. Voicing, saving, and naming each one is the busywork. That busywork is what the automation removes.

Why use Make if ElevenLabs can make a voiceover itself?

Fair question. The ElevenLabs app voices one script when you paste it in, then you download and file the audio by hand. Perfect for a single clip, painful for fifty.

Make turns it into a batch. It watches the sheet, sends every row to ElevenLabs, and files each audio file with no clicking. The voice model does the speaking; Make does the repeating and the filing. The tool and the model split the work, and that split is what makes a library of audio painless to produce.

What do you need before you start?

• A Make account. The free 1,000 operations a month covers plenty of clips.
• An ElevenLabs API key from your ElevenLabs account. New to AI tools and keys? Our how to use Claude guide explains API keys in general.
• A Google account with a Drive folder for the audio files.
• A Google Sheet with a Script column, one voiceover per row.

Two Make words, once. A scenario is one automation, the whole sheet-to-Drive chain. A module is one box in it. Three boxes, one scenario.

How does the workflow work, step by step?

Three modules, left to right:

Module	App	What it does
1. Trigger	Google Sheets	Fires when you add a row of script text
2. Voice	ElevenLabs	Turns the script into spoken audio
3. Output	Google Drive	Uploads and saves the audio file

Step 1: Set up the script sheet

Create a scenario in Make and add Google Sheets, Watch New Rows, connect your account, and point it at a sheet with a Script column. Each row you add is one voiceover.

Step 2: Let ElevenLabs voice it

Add ElevenLabs, Create a speech synthesis, paste your ElevenLabs API key, pick a voice, and map the Script column from Step 1. Keep scripts punchy for the cleanest reads:

Welcome to the east wing. The painting before you was finished in
1923 and nearly lost to a fire two years later. Look closely at
the lower left corner, where the artist signed twice.

Choosing one voice and sticking with it keeps a whole set sounding like one narrator.

Step 3: Save the audio to Drive

Add Google Drive, Upload a File, choose the folder, and map the audio from Step 2, named from the row. Now every script you add becomes a saved, named clip.

How do you run it and check the result?

Click Run once after adding a test script. When I tested this, a row of scripts turned into a folder of clean voiceovers in a few minutes, and the thing that mattered was picking one voice and keeping scripts short, since long run-on sentences read less naturally. Tune your voice and scripts, then turn the scenario on.

After that, voicing content stops being a chore and becomes a list. You write the words, and the audio appears in the background, ready to drop into an app, a video, or a tour.

What does this cost to run?

Piece	Free tier	If you outgrow it
Make	1,000 operations/month free	Core plan from about $9/month
ElevenLabs	Free monthly character allowance	Paid plans by characters voiced
Google Drive	Free	Free
Google Sheets	Free	Free

ElevenLabs bills by characters voiced, with a free monthly allowance that covers small projects. Watch your script volume on the free tier. More on Make’s side in our Make guide.

What can go wrong, and how do you avoid it?

• The reads sound robotic. Keep scripts short and natural; long sentences read worse. Punctuation helps pacing.
• The voice changes between clips. Pick one voice and keep it for the whole set.
• You run out of characters. ElevenLabs free tiers cap monthly characters; batch what you need.
• Files overwrite each other. Name each upload from the row so clips never collide.

Want more of this pattern? Our Make AI scenarios roundup has the next ideas.

How do you build this in Zapier or n8n instead?

The three jobs do not change, only the names do.

Job	Make	Zapier	n8n
Catch a script	Watch New Rows	New Spreadsheet Row trigger	Google Sheets Trigger node
Voice it	ElevenLabs speech	ElevenLabs action	ElevenLabs / HTTP node
Save the file	Upload a File	Google Drive Upload	Google Drive node

Make and Zapier are the gentlest for a first build. Zapier vs Make vs n8n compares all three.

Common questions

Why not just use the ElevenLabs app?

For one clip, do. This build is for volume: a list of scripts becomes a folder of saved, named audio with no clicking, which the app cannot do on its own.

Can I use a different voice tool?

Yes. Swap ElevenLabs for OpenAI, Google, or another voice model. The sheet trigger and Drive upload do not change.

Can I clone my own voice?

ElevenLabs offers voice cloning on its paid tiers. Set it up there, then pick that voice in the Make step.

Can it post the audio somewhere automatically?

Yes. Add or swap the final module for your podcast host, site, or app. Saving to Drive first keeps it simple to check.

Does Claude do voice?

No, which is why this build uses ElevenLabs. Claude is for reading and writing; speaking needs a voice model.

Sources and docs

• Creating a scenario (Make Help)
• ElevenLabs API docs
• Upload files to Google Drive (Google)
• ElevenLabs on Make (integrations)
• Speech synthesis — Grokipedia

Last reviewed: May 2026. Make, ElevenLabs, and Google update their interfaces; check the official pages for exact button names.

You may also like

• AI Automation for Beginners (the hub)
• Transcribe a recording with Whisper + Make
• Generate images from a sheet with ChatGPT
• Make.com Complete Beginner’s Guide
• How to use Claude AI
• Zapier vs Make vs n8n: which to start with
• The AI Tools Directory