Update google_generative_ai_conversation.markdown to document support for Gemini's new TTS capabilities

tl-sl · lanthaler · commit 7606a041bacc · 2025-06-01T12:06:22.000Z
diff --git a/source/_integrations/google_generative_ai_conversation.markdown b/source/_integrations/google_generative_ai_conversation.markdown
@@ -3,6 +3,7 @@ title: Google Generative AI
 description: Instructions on how to integrate Google Generative AI as a conversation agent
 ha_category:
   - Voice
+  - Text-to-speech
 ha_release: 2023.6
 ha_iot_class: Cloud Polling
 ha_config_flow: true
@@ -14,6 +15,7 @@ ha_integration_type: service
 ha_platforms:
   - conversation
   - diagnostics
+  - tts
 related:
   - docs: /voice_control/voice_remote_expose_devices/
     title: Exposing entities to Assist
@@ -25,7 +27,7 @@ related:
     title: Google Generative AI
 ---
 
-The Google Generative AI integration adds a conversation agent powered by [Google Generative AI](https://ai.google.dev/) in Home Assistant. It can optionally be allowed to control Home Assistant.
+The Google Generative AI integration adds a conversation agent and text-to-speech engine powered by [Google Generative AI](https://ai.google.dev/) to Home Assistant. It can optionally be allowed to control Home Assistant.
 
 Controlling Home Assistant is done by providing the AI access to the Assist API of Home Assistant. You can control what devices and entities it can access from the {% my voice_assistants title="exposed entities page" %}. The AI is able to provide you information about your devices and control them.
 
@@ -188,6 +190,32 @@ response_variable: generated_content
 
 {% endraw %}
 
+### Action `tts.speak`
+
+The `tts.speak` action is the modern way to use TTS. Add the `speak` action, select the Google Generative AI TTS entity, select the media player entity or group to send the TTS audio to, and enter the message to speak.
+
+Text-to-speech (TTS) generation is controllable, meaning you can use natural language to structure interactions and guide the style, accent, pace, and tone of the audio. You can change the way the text is spoken directly in the message by, e.g. entering "Say cheerfully: Have a wonderful day!" instead of just "Have a wonderful day!".
+
+For more options about `speak`, see the Speak section on the main [TTS](/integrations/tts/#service-speak) building block page.
+
+In YAML, your action will look like this:
+
+{% raw %}
+
+```yaml
+action: tts.speak
+target:
+  entity_id: tts.google_generative_ai_tts
+data:
+  media_player_entity_id: media_player.tv
+  message: Say cheerfully: Have a wonderful day!
+  options:
+    voice: <voice-id>
+    model: <model-id>
+```
+
+{% endraw %}
+
 ## Video tutorial
 
 This video tutorial explains how Google Generative AI can be set up, how you can send an AI-generated message to your smart speaker when you arrive home, and how you can analyze an image taken from your doorbell camera as soon as someone rings the doorbell.
@@ -204,4 +232,4 @@ logger:
     homeassistant.components.conversation: debug
     homeassistant.components.conversation.chat_log: debug
     homeassistant.components.google_generative_ai_conversation: debug
-```
+```
