Using SEPIA with OpenAuto

[PaulPoule]

Hello,

Do you think SEPIA would work with OpenAuto Pro (https://bluewavestudio.io/index.php/our-products/2-openauto-pro), which includes Raspbian and some custom car-oriented software?

I'm a noob looking for a head unit with offline voice control (I'm most likely not the only one!) and SEPIA seems perfect for this. I saw your instructions on how to create a scenario for playing a music playlist on Windows from an Android client but I'm not sure about applying them to my just one host running Raspbian.

Any pointers or help you can provide will be greatly appreciated! Thanks.

[fquirin]

Hi,

that looks like a very interesting project! I'm pretty sure there are options to bring these two things together but I'd need to look a bit closer at openAuto to understand how it actually works.

Since there is an official SEPIA Android app (which can use Google offline/online and SEPIA speech recognition server) I was wondering if it might show up somehow in the openAuto interface (with some minor changes)?

Besides that it is definitely possible to run SEPIA on the same Raspberry PI + touchscreen configuration used by openAuto, so one might be able to switch between the two apps until everything is fully supported. I'm currently working on a new all-in-one Raspberry Pi4 system (https://twitter.com/sepia_fw/status/1150891317305794561) which might also be strong enough to run the speech recognition together with all the other SEPIA components, but I haven't tested that yet. Usually I run the speech recognition server on a x86 system (not a RPi).

[PaulPoule]

It's interesting you should mention the RPi4, would you recommend using nothing else than a 4GB RPi4 to attempt running Openauto and all SEPIA components? I'm not sure about CPU requirements.

[fquirin]

In my latest tests the RPi4 with 4GB RAM was blazing fast and could easily handle SEPIA-Home (complete server stack) AND the SEPIA client. It might be just strong enough to even run the ASR ^^.