How to Download Google TTS Audio as MP3 (Step-by-Step Guide 2026)

Published April 21, 2026 · 6 min read

TL;DR: Install the free TTS Audio Downloader extension for Chrome or Edge. Open the Google Cloud TTS demo page, type your text, click Play, then click the Download MP3 button that appears next to the play button. Done in under 30 seconds. The basic plan gives you 5,000 characters per day with no sign-up required.

The Problem: Google TTS Has No Download Button

Google Cloud Text-to-Speech offers one of the highest-quality TTS engines available, with over 220 voices across 40+ languages. The demo page lets anyone try these voices for free — type your text, select a voice, and click Play to hear it.

But there is one critical missing feature: there is no download button. You can listen to the audio, but you cannot save it as an MP3 or WAV file. If you want the audio for a video voiceover, a language learning exercise, or an accessibility project, you are stuck.

This guide covers three methods to download Google TTS audio, from the easiest (a browser extension) to the most technical (the API). Pick the method that fits your skill level and needs.

Method 1: TTS Audio Downloader Extension (Recommended)

The fastest way to download Google TTS audio is with a browser extension that adds a download button directly to the demo page. Here is how it works:

Step 1: Install the extension

Add TTS Audio Downloader from the Chrome Web Store. It also works on Microsoft Edge. No account, no sign-up, no credit card.

Step 2: Open the Google Cloud TTS demo

Go to the Google Cloud Text-to-Speech demo page. You will see a text input area where you can type or paste your text. Select your preferred language and voice from the dropdown menus.

Step 3: Type your text and click Play

Enter the text you want to convert to speech. You can type up to 5,000 characters per day on the basic plan. Select the voice you want (Google offers Standard, WaveNet, Neural2, and Studio voices), adjust the speed if needed, and click the Play button.

Step 4: Click Download MP3

After you click Play, a Download MP3 button appears right next to the play button. Click it to save the audio file to your computer instantly. You can also choose WAV format if you need lossless quality.

That is it. The entire process takes less than 30 seconds.

What about long text?

The Google TTS demo has a character limit per request. TTS Audio Downloader handles this automatically: it splits your long text into chunks, synthesizes each one, and merges them into a single audio file. You do not need to manually break up your text or stitch files together.

Method 2: Browser Developer Console

If you prefer not to install an extension, you can use your browser's developer tools to capture the audio file. This method is free but requires a few technical steps.

Step 1: Open DevTools

On the Google TTS demo page, press F12 (or Cmd+Option+I on Mac) to open the developer console. Click on the Network tab.

Step 2: Play the audio

Type your text in the demo page and click Play. Watch the Network tab — you will see new requests appear. Look for a request that returns audio data (it will typically be an XHR or Fetch request with a large response size).

Step 3: Save the audio file

Right-click on the audio request and select "Save response as..." or "Copy as cURL" and then run the command in your terminal. The downloaded file will be in the format the API returns (usually base64-encoded audio that you need to decode).

Drawbacks of this method

  • You need to repeat the process for every single audio clip
  • Long text is split into multiple requests — you need to download and merge each segment manually
  • The response is often base64-encoded, requiring an extra decoding step
  • It does not work well if the demo page changes its request format

This method works in a pinch, but it is not practical for regular use or long text. If you need to download TTS audio more than once, the extension method is significantly faster.

Method 3: Google Cloud TTS API

For developers and power users, the official Google Cloud Text-to-Speech API gives you full programmatic access to all voices and features. However, it requires setup.

What you need

  • A Google Cloud Platform (GCP) account
  • A credit card on file (even for the free tier)
  • Enable the Text-to-Speech API in the GCP console
  • Generate an API key or service account credentials
  • Write code (Python, Node.js, curl, etc.) to make API calls

Pricing

Google offers a free tier of 1 million characters per month for Standard voices and 1 million characters for WaveNet voices (first 12 months only). After that:

  • Standard voices: $4 per 1 million characters
  • WaveNet voices: $16 per 1 million characters
  • Neural2 voices: $16 per 1 million characters

When to use the API

The API makes sense if you are building a product that generates TTS audio programmatically, or if you need to process thousands of audio files in batch. For occasional downloads from the demo page, the extension is faster and easier.

Comparison: Extension vs DevTools vs API

Feature Extension DevTools API
Setup time 10 seconds None 30-60 minutes
Coding required No Minimal Yes
Cost Free (5,000 chars/day) Free Free tier, then $4-16/1M chars
Output format MP3, WAV Raw response MP3, WAV, OGG, more
Long text handling Auto-split + merge Manual Manual or custom code
Bulk downloads Yes (Pro plan) No Yes (with code)
Additional platforms Azure, ChatGPT Google TTS only Google TTS only

For most users, the browser extension is the clear winner: one-click download, no coding, no API key, and it handles long text automatically. It also works on Azure Speech Studio and ChatGPT, which gives you three TTS platforms in one tool.

Bonus: Download Audio from Azure and ChatGPT Too

TTS Audio Downloader is not limited to Google TTS. It also adds download buttons to:

  • Azure Speech Studio: Microsoft's TTS demo with high-quality neural voices. The same one-click download button appears after you play your text.
  • ChatGPT: Download voice output from any ChatGPT conversation. Use "Download All" to save every voice message in a thread at once — included in the basic plan at no extra cost.

All three platforms are supported with a single extension. No need to install separate tools for each service.

Basic vs Pro Plan

TTS Audio Downloader offers a generous basic plan that covers most casual use cases:

  • Basic (free): 5,000 characters per day, MP3 and WAV export, ChatGPT Download All, all 3 platforms. No sign-up or credit card required.
  • Pro ($0.99/month or $4.99 one-time): Unlimited characters, unlimited bulk mode, custom file naming, AAC export for ChatGPT (native quality, smaller file size).

The one-time $4.99 option gives you lifetime Pro access — no recurring subscription to worry about.

FAQ

Is downloading Google TTS audio legal?

Yes. The Google Cloud Text-to-Speech demo is a publicly available page that Google provides for anyone to try their TTS voices. You are downloading audio that was generated from a free demo. The extension is officially listed on the Chrome Web Store and does not bypass any access controls.

What audio formats are supported?

The basic plan supports MP3 and WAV export. Pro users also get AAC export for ChatGPT voice messages (native quality, smaller file size). You can switch formats with one click on the download button.

Can I download long text as a single audio file?

Yes. TTS Audio Downloader automatically splits long text into chunks, synthesizes each one through Google TTS, and merges them into a single MP3 or WAV file. No manual splitting required. This works on the basic plan with the 5,000 character daily limit.

Does it work with Azure Speech Studio and ChatGPT too?

Yes. TTS Audio Downloader works on three platforms: Google Cloud TTS demo, Azure Speech Studio, and ChatGPT. The same one-click download button appears on all three. You do not need separate extensions for each platform.

Can I download audio in bulk?

Yes. The basic plan includes 3 bulk downloads per day. The Pro plan unlocks unlimited bulk mode, which is useful for content creators or language learners who need to generate multiple audio files in a session.

Does the extension collect my text or audio data?

No. All text processing and audio conversion happens entirely within your browser. Your text is never sent to any server other than the TTS platform itself (Google, Azure, or ChatGPT). The extension does not include analytics or tracking code.