Update LLM API part

source/_posts/2024-06-05-release-20246.markdown

@@ -76,8 +76,8 @@ Our voice assistant brain is called a **conversation agent**.
 It is responsible for understanding the intention behind the spoken command,
 performing an action, and generating a response.
 
-Since the beginning of our voice journey, we proposed you to switch your
-conversation agent for a LLM-based one. This led to some very funny experiments,
+Since the beginning of our voice journey, we allowed you to switch your
+conversation agent for an LLM-based one. This led to some very funny experiments,
 such as our [infamous interview with Mario](https://www.youtube.com/watch?v=eLx8_NAqptk).
 
 Up until now, these two worlds (our own Home Assistant conversation agent
@@ -88,7 +88,7 @@ Today we're happy to announce that we are closing this gap!
 
 <lite-youtube videoid="3V9Pj6XCels" videotitle="Temporary video that needs to be replaced"></lite-youtube>
 
-When setting up a LLM-Based conversation agent you can decide to let your
+When setting up an LLM-Based conversation agent you can decide to let your
 conversation agent control your home with a flick of a switch.
 
 <p class='img'>
@@ -96,7 +96,12 @@ conversation agent control your home with a flick of a switch.
     Temporary screenshot that needs to be replaced.
 </p>
 
-This is already available on Open AI and Google AI.
+This release makes this available to [OpenAI](/components/openai_conversation/) and [Google AI](/components/google_generative_ai_conversation/). To make it easier to get started with LLMs, we have updated these integrations with recommended model settings that strike the right balance between performance, speed and cost. If you had them set up previously, we recommend enabling the recommended settings and emptying the instructions.
+
+Our recommended model settings perform equally well for voice assistant tasks. Google is 14x cheaper than OpenAI, but OpenAI is better at answering non-smart home questions. We are preparing a blog post with a deep dive into the research that went into this feature, coming soon.
+
+_Thanks to our AI team [@shulyaka](https://github.com/shulyaka), [@tronikos](https://github.com/tronikos), [@allenporter](https://github.com/allenporter), [@synesthesiam](https://github.com/synesthesiam), [@jlpuffier](https://github.com/jlpuffier) and [@balloob](https://github.com/balloob) for this feature!_
+
 
 ## Assist: Media player intents
 
@@ -116,7 +121,7 @@ the logic of deciding which exposed media player to target based on the intents
 triggered.
 
 We paired these new sentences with our "Context awareness" feature _(The ability
-to implicitly target the same area in which the voice assistant is)_. 
+to implicitly target the same area in which the voice assistant is)_.
 
 Thanks to that, we are now able to provide very simple and user friendly
 sentences to control your media players, such as:
@@ -172,7 +177,7 @@ _Note: Add a picture uploader to picture-card-editor (#18695) @karwosts__
 Just like the last release, this release keeps on improving our data tables.
 
 When we introduced grouping of data in the tables, you've been asking for a way
-to collapse and expand those groupings, so, last release, we did! But then 
+to collapse and expand those groupings, so, last release, we did! But then
 quickly realized that it was not enough, and you wanted to be able to collapse
 and expand all groups at once. So, we did that for this release!
 
@@ -297,7 +302,7 @@ platinum grade quality:
 _Note to remove: Processed possible noteworthy up to PR #118365_
 
 Possible other candites:
- 
+
 - Add support for Aranet radiation devices ([@Anrijs] - [#115239])
 - Add Workarea cutting height to Husqvarna Automower ([@Thomas55555] - [#116115])
 - Add Venstar HVAC stage sensor ([@jhollowe] - [#107510])