Google Cloud TTS
Enterprise-grade text-to-speech with WaveNet and Neural2 voices.
On this page
Requirements
- Google Cloud project with billing enabled
- Cloud Text-to-Speech API enabled
- Service account with Text-to-Speech Admin (or equivalent) permissions
- Service account JSON key file
- VoiceThisText account with provider connections enabled
Create Service Account Key
- In Google Cloud Console, go to APIs & Services → Enabled APIs and enable Text-to-Speech API.
- Go to IAM & Admin → Service Accounts and create a service account.
- Grant it Text-to-Speech Admin (or a role that allows TTS synthesize).
- On the Keys tab, create a JSON key and download the file.
Keep the JSON key secure. If it is ever exposed, revoke it and generate a new one.
Connect Google Cloud
- In VoiceThisText, go to Providers.
- Click Add Provider and choose Google Cloud.
- Upload your service account JSON key.
- Save. VoiceThisText fetches available voices for your project.
Voices & Models
Google Cloud TTS offers multiple voice families; availability varies by language:
- Standard — baseline voices
- WaveNet — neural, higher quality
- Neural2 — newest neural voices with improved prosody
VoiceThisText lists only the voices your project can access in the regions supported by Google Cloud TTS.
Generating Audio
- Select the Google Cloud provider when creating an audio generation.
- Pick a voice (WaveNet/Neural2/Standard) and adjust speaking rate or pitch if needed.
- Generate. VoiceThisText sends the request to Google Cloud and stores the returned audio and transcript timing (if enabled).
- Embed the player or use the WordPress plugin to publish.
Troubleshooting
- PERMISSION_DENIED — ensure the Text-to-Speech API is enabled and the service account has TTS permissions.
- Invalid JSON key — re-download the key and paste the full JSON (including newlines).
- Voice not available — voice may be region or language limited; pick another voice or language code.
- Quotas exceeded — check Google Cloud quotas and increase limits or reduce request rate.