-
Yes, provided your language is supported and you have hardware powerful enough to run local
- text-to-speech and speech-to-text models at a speed that is acceptable to you. Speech-to-text is
- the main limiting factor for many languages to run locally, as it has mixed results and often
- requires powerful hardware.
-
We recommend using at least an Intel N100 or equivalent processor;
- this will allow you to use OpenAI’s Whisper Base model for speech-to-text locally. This model
- runs reasonably fast for languages that have large public datasets to train on, such as English
- and Spanish. However, for languages with less data available, you will need Whisper’s Small or
- Large models that require significantly more powerful hardware to run. For some languages, no
- public datasets exist yet for local models to be trained on by OpenAI, and until they exist and
- they train models, you will not be able to run those languages fully locally.
+
Yes, provided your language is supported. For some languages, you can set up Assist and your
+ Voice Preview Edition to use a Focused Local model, which uses Speech-to-Phrase add-on. It can run
+ locally and accurately on lower-power hardware, by generating a local speech-to-text model
+ specifically for your Home Assistant installation. It is limited to predefined sentences aimed at
+ controlling your home, but not able to process general speech. For instance, it could turn on a
+ device, but would not be able to add something to your shopping list.
+
+
For other languages, Speech-to-Phrase may not be supported, which will require Fully Local
+ speech-to-text solution, such as the Whisper add-on. Fully local speech-to-text requires powerful
+ hardware to be accurate and responsive. If you wish to use OpenAI’s Whisper, we recommend using at
+ least an Intel N100 or equivalent processor. This will allow you to use the Whisper Base model for
+ speech-to-text locally. This model runs reasonably fast for languages that have large public
+ datasets to train on, such as English and Spanish. However, for languages with less data
+ available, you will need Whisper’s Small or Large models that require significantly more powerful
+ hardware to run.