Skip to main content

Google Translate TTS smart home integration, free and open source

Google Translate TTS integration for Gladys Assistant

The free voice of Google Translate for Gladys announcements: no account, no API key.

View on GitHubAll integrations

Gives Gladys the free voice of Google Translate: the scene announcements are spoken by it on your speakers. No account, no API key, like the google_translate text-to-speech of Home Assistant (gTTS).

What you get​

  • A voice for Gladys (Gladys 5.3.0 or later): once selected, the Talk on a speaker scene action speaks with Google Translate on your speakers (Sonos, Google Cast, AirPlay…).
  • Texts in 33 languages, in the language of each user automatically, with regional accents for English, French, Spanish and Portuguese, and a slow reading.
  • Long texts (up to the 2,000 characters Gladys sends) are cut at the end of sentences and joined into a single clip.

Before you start: what this voice is​

  • It is the voice of the Google Translate website, used the way gTTS has used it for years. It is not an official Google service: there is no guarantee, and Google may change it, limit it or stop it at any time. The integration then fails visibly (Supervision, scene log), it never falls back to another voice on its own.
  • Every text spoken is sent to Google (with the IP address of your connection), under the Google privacy policy. Do not use it for texts you want to keep at home.
  • An Internet connection is required.
  • Not affiliated with Google. Google Translate is a trademark of Google LLC.

Configuration​

  1. Install the integration from the catalog, then open its Configuration tab.
  2. Language of the voice: Automatic speaks the language of the user Gladys answers, and the language of the first administrator for a scene announcement (French when Gladys does not know it). Or force one language.
  3. Accent: a regional voice (English of the United States, the United Kingdom, Australia or India; French of France or Canada; Spanish of Spain or Mexico; Portuguese of Brazil or Portugal). It applies when the language spoken is its own; the other languages keep their usual voice. The usual English voice is the British one.
  4. Slow reading: speaks more slowly, like the slow button of Google Translate.
  5. Save, then press Test the voice: it asks Google Translate for a test sentence and shows the length of the clip received.
  6. Open Integrations → Artificial Intelligence and choose Google Translate TTS in the Voice card.

Using it in scenes​

Add a Talk on a speaker action to a scene, pick a speaker and type the text. Gladys asks this integration for the clip, then serves it to the speaker on your local network.

The voice assistant of Gladys stays text-only with a voice integration: its page runs over HTTPS, and the clip is served over the local network in HTTP, which the browser blocks. This is a limit of Gladys, the same for every voice integration.

Limits​

  • Google Translate takes 200 characters per request: a longer text is cut at the end of sentences (then clauses, then words) and requested one part at a time, about 0.3 s each. The 2,000 characters Gladys sends at most make about 12 requests, 4 seconds and a 1.5 MB clip of 3 minutes: well within the 30 seconds Gladys waits.
  • Each part is read with its own intonation, so a long text has short pauses between parts.
  • A clip already made (same text, voice and speed) is kept in memory (the 16 latest), and one announcement on several speakers asks Google once.
  • When Google refuses too many requests (HTTP 429), the integration waits for the next announcement: it does not insist.

Troubleshooting​

  • Supervision shows whether Google Translate answers and, if not, why (no Internet, too many requests, the free voice changed…).
  • A failed announcement is written in the logs of the integration, and the scene action fails in the scene log.
  • "The free voice may have changed": Google has modified its website; look for an update of the integration.
  • Start the container with LOG_LEVEL=debug to see every request.

Configuration settings​

These are the settings Google Translate TTS asks for in its configuration screen in Gladys.

SettingTypeRequiredDescription
The free voice of Google TranslatesectionNoNo account or key: the voice of the Google Translate website, as with gTTS. Unofficial and without guarantee: Google may change or limit it. Texts are sent to Google. Then select this voice on the Artificial Intelligence page.
Language of the voiceselectNoAutomatic: the language of the user Gladys answers, or of the first administrator for an announcement (French when unknown).
AccentselectNoRegional voice used when the language spoken is its own; the others keep their usual voice.
Slow readingbooleanNoSpeaks more slowly, like the slow button of Google Translate.

How to install Google Translate TTS in Gladys​

  1. In Gladys, open Integrations: Google Translate TTS appears in the catalog, next to the native integrations, with a community badge.
  2. Click Install. Gladys pulls the Docker image (ghcr.io/guim31/gladys-google-translate-tts:1.0.0), starts it in a sandbox isolated from the core, and generates the integration's interface (devices, discovery and configuration).
  3. Open the Configuration screen of the integration, fill in the settings, and save.
  4. You can also install it directly from its repository URL: https://github.com/guim31/gladys-google-translate-tts.

Google Translate TTS requires Gladys >=5.3.0. The catalog inside Gladys refreshes every hour, so a new version becomes available at most one hour after its release.

Not running Gladys yet? It is free and open source: follow the installation guide to get started.

About external integrations​

Google Translate TTS is an external integration: a community integration packaged as a Docker container and published on GitHub, that Gladys installs in one click and runs in a sandbox isolated from its core. It is published and maintained by guim31, not by the Gladys core team.

Subscribe to the Gladys Assistant newsletter

A few emails per month about new releases and project news. Sent by Pierre-Gilles Leymarie, founder of the project. Unsubscribe anytime 🙂
Last updated on