diff --git a/source/_posts/2024-06-05-release-20246.markdown b/source/_posts/2024-06-05-release-20246.markdown index 877aa2e7ae9..3c8165ea31f 100644 --- a/source/_posts/2024-06-05-release-20246.markdown +++ b/source/_posts/2024-06-05-release-20246.markdown @@ -49,11 +49,11 @@ Enjoy the (beta) release! - [Dipping our toes in the world of AI using LLMs](#dipping-our-toes-in-the-world-of-ai-using-llms) -- [Assist: Media player intents](#assist-media-player-intents) +- [Assist: Improved media player commands](#assist-improved-media-player-commands) - [Show sections conditionally](#show-sections-conditionally) - [Setting a dashboard background](#setting-a-dashboard-background) - [Data tables improvements](#data-tables-improvements) -- [Updates Matter](#updates-matter) +- [Matter turns 1.3](#matter-turns-13) - [Ability to disable the expiring of login tokens](#ability-to-disable-the-expiring-of-login-tokens) - [Tag entities!](#tag-entities) - [Collapsable sections for blueprints!](#collapsable-sections-for-blueprints) @@ -96,50 +96,42 @@ conversation agent control your home with a flick of a switch. Temporary screenshot that needs to be replaced.
-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 accuracy, speed and cost. If you had them set up previously, we recommend enabling the recommended settings and emptying the instructions. +This release makes it available for our [OpenAI](/components/openai_conversation/) and [Google AI](/components/google_generative_ai_conversation/) integrations. To make it easier to get started with LLMs, we have updated them with recommended model settings that strike the right balance between accuracy, 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 +## Assist: Improved media player commands -We released new voice intents in 2024.3: The ability to control media players +We have introduced new media player intents that allow you to do more while saying less. Thanks to +two new features, you can say the following voice commands to control media players in the same area: -- Pausing playback -- Resuming Playback -- Setting the volume of a media player -- Playing the next media in the queue +- "Pause" +- "Resume" +- "Next" +- "Set the volume to 50%" Up until now, we were only proposing sentence targeting a specific entity by its name. Due to this limitation, these intents were not the most user friendly to use, as the sentences were pretty heavy to say: _"Skip to the next song on the TV"_. -We are now proposing sentences targeting an area, Home Assistant will handle all -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)_. - -Thanks to that, we are now able to provide very simple and user friendly -sentences to control your media players, such as: - -- Pause -- Resume -- Next -- Set the volume to 50% +We added two features to allow us to get to the smallest sentences possible. Context awareness makes +our voice assistant aware of the devices in the same area as the satellite. On top of that we have created +a smart matching strategy that finds the right media player to target. For example, if you say "pause", +the voice assistant will automatically target the media player that is playing.