Skip to content
Cloud Speech Install

← Back to all guides

Setup guide

Set up Google Cloud Text-to-Speech

Google Cloud Text-to-Speech has Standard, WaveNet, Neural2, Chirp HD, and Chirp 3 HD voices with a generous monthly free tier. This guide walks you through creating a restricted API key. No developer experience needed. It takes about 10 minutes.

What you'll need

  • A Google account and a Google Cloud account with billing enabled (the monthly free tier still applies)
  • About 10 minutes
  1. 1

    Create a Google Cloud project

    1. Go to the Google Cloud Console and sign in with your Google account
    2. If this is your first visit, accept the terms; new accounts get free trial credits
    3. Click the project selector at the top of the page, then New project
    4. Name it, e.g. cloud-speech-tts, and click Create
    5. Make sure billing is enabled for the project (Menu → Billing); the API requires it even if you stay inside the free tier
  2. 2

    Enable the Text-to-Speech API

    1. With your project selected, open the Cloud Text-to-Speech API page (or search "Text-to-Speech" in APIs & Services → Library)
    2. Click Enable

    Planning to use Gemini voices?

    Gemini voices (the ones with bare names like Achernar) also need the Vertex AI API enabled on the same project. Without it, those voices fail with a 403 error while all other Google voices keep working. If you restrict your API key in the next step, include the Vertex AI API in the restriction too.
  3. 3

    Create a restricted API key

    1. Go to APIs & Services → Credentials in the Cloud Console
    2. Click Create credentials → API key
    3. Copy the key that appears
    4. Click Edit API key (or the key's name) to restrict it
    5. Under API restrictions, choose Restrict key and select only Cloud Text-to-Speech API
    6. Click Save

    Security warning

    Restricting the key means it can't be misused for other Google services if it ever leaks. Keep it secret, and regenerate it from the Credentials page if needed.
  4. 4

    Connect the extension

    1. Click the extension icon in your browser toolbar
    2. Open Settings → Google Cloud TTS
    3. Paste your API key
    4. Click Save & test

    Once the test passes, the Google voices appear in the voice picker. Press ▶ to preview any voice and ★ to favorite the ones you like. Then highlight text on any page, right-click, and choose Read aloud, or press Ctrl/Cmd+Shift+S.

Costs

The free tier renews every month: 1 million characters for WaveNet/Neural2 voices and 4 million characters for standard voices. Beyond that, standard voices cost about $4 per 1 million characters and WaveNet/Neural2 about $16 per 1 million characters; Chirp HD and Chirp 3 HD voices are priced higher. Check the official Google Cloud TTS pricing page and our provider comparison.

Remove access when you're done

  1. Open APIs & Services → Credentials, find your API key, and choose Delete from its ⋮ menu. The key stops working within a few minutes.
  2. Optionally disable the APIs under APIs & Services → Enabled APIs (Text-to-Speech, and Vertex AI if you enabled it for Gemini voices), or shut down the whole project under IAM & Admin → Settings.
  3. In the extension, open Settings → Google Cloud TTS and clear the saved key (or turn the provider off).

Prefer the command line?

With the gcloud CLI, this enables the APIs and creates the same restricted key as the steps above: 

gcloud auth login
gcloud config set project YOUR_PROJECT_ID
gcloud services enable texttospeech.googleapis.com aiplatform.googleapis.com

gcloud services api-keys create --display-name="Cloud Speech" \
  --api-target=service=texttospeech.googleapis.com \
  --api-target=service=aiplatform.googleapis.com
# The keyString in the output is the API key for the extension.

And to remove it all later:

gcloud services api-keys list          # find the key's UID
gcloud services api-keys delete KEY_UID
gcloud services disable texttospeech.googleapis.com aiplatform.googleapis.com

Troubleshooting

"Credentials are missing or invalid"

Double-check the key you pasted; a stray space is the most common cause. Make sure the Text-to-Speech API is enabled on the same project the key belongs to, and that the key's API restriction includes Cloud Text-to-Speech. Then click Save & test again.

"Access denied" errors

Your key is valid but lacks permission. It must be allowed to call the Text-to-Speech API, and your account must be in good standing (no billing hold).

For no audio, missing voices, or keyboard shortcut problems, see the troubleshooting guide.

Prefer a different provider? See Amazon Polly, Azure Speech, or OpenAI.