That is an interesting video!!
Can I just ask, who actually wants to be able to ‘skip ahead 60 seconds’ while playing music though??
CloudConstable, what do you mean “gesture recognition for mute” and “3D sensor”? Is it a voice command or gesture with hands or something else? I think if you say wake-word then a volume of current played music must go down. Quick mute command is good but user knows wake-word better.
When you can create volumio plugin, then volunteers will stand in queue 
.
PS. I would use it ‘skip ahead’ command for Iron Maiden’s song Satelite 15 best part starts in second half.
Here’s a Halloween message from our new animated AI DJ, Viola:
I made little research. Competition is hard but you have big chance because no ones can play music on our hifi. Voice assistant will chat with you, it will select song, but it will play it only on itself speaker. If you want play song on your hifi, you will need connect it via chromecast (Google closed the api), bleutooth or analog from 3.5mm jack. No option is good, if you have spend money on good DAC.
I’m just getting into the whole “voice control” thing, and am currently converting the lights and sockets in my home to be controlled by Amazon’s Alexa. I started doing it for fun as the Dot devices themselves were dirt-cheap, but I’m quite surprised at how useful I’m actually finding it. Nothing to do with Volumio, I know, but my roundabout point is, nobody will really know how useful they will find voice control for Volumio is until they’ve tried it. I’d much rather be in the position to test it and if I don’t like it, turn the feature off, than not have it and constantly wonder how good it might actually be.
Very wise point. And man, I love your avatar pic!
A Snips.ai plugin would be great. I moved away from Volumio to an Echo dot with Alexa, because of the Wife Acceptance Factor (WAF), but would love to come back to Volumio, using voice control from snips and using a ReSpeaker hat. Perhaps there should be a separate implementation, so external voice control could control the existing Volumio? Or?
Playing music by using voice control is really great! Once you are using it, you won’t go back using apps or small touch screens on the device…
Voice control and AI in general seems to be gaining popularity, so at some point it will probably hurt Volumio if it won’t offer this. I am just about to start discovering the possibilities and I have a question. There is more and more “assistants” Google, Alexa, Siri,… to name just a few, can all be integrated in volumio or will it be “locked” to a single one?
Having a switch/toggle in options to enable or disable AI should probably satisfy both the pro and con users?
I’d say voice UI is the way things are headed. Even my Mum now uses Google home and never really got the hang of a smartphone so that speaks volumes (pardon the pun). What I will question is why roll your own solution rather than get one of the big three to do your heavy lifting?
For me Google assistant is better by a country mile with natural language compared to say Alexa, I have no experience of Siri in any meaningful way so I can’t compare with Apple. I’d look to offer Google integration first if it were me…
Hi Everyone,
Happy New Year!
I’m glad to see that the interest amoung the Volumio community has increased somewhat! It is long past time for an update from me, and I apologize that our communications have been too few and far between.
Unfortunately, we have encountered some delays in releasing our initial trial application. The primary reason for this is that, in a more ‘real world’ test that we set up in a simulated living room before Christmas, we found that the far field voice recognition accuracy of our solution was simply not up to snuff. We’re using the IBM Watson Speech To Text (STT) service, accessed via IBM Cloud, as a key component of this solution, and it turned out that this service seems not to be very well tuned for far field applications by default.
Even more unfortunately, one of the key tuning parameters that we can use to improve the performance of the Watson STT service, which is called using a custom grammar by IBM, has encountered a production issue which is being worked on by IBM. As yet, we have no specific ETA on the fix for this issue, but the expectation is that it should be fixed this month. Meanwhile, we’re exploring other alternatives.
I will provide a further update when I have more specific news to share!
If you’re looking for more information on our progress as it happens, I encourage you to check my blog or sign up for our mailing list. My blog can be found at: cloudconstable.com/news-events/
You’ll also find a “Subscribe to our Newsletter” button on the same page!
I hope we’ll be talking more about, well, a talking AI assistant for Volumio, very soon!
We’ve released a free trial version AI Voice Assistant for alpha testing and validation. It is supported only on MS Windows for now. If you’d like to try it, you can download and install it from here:
drive.google.com/open?id=141eDz … N0PlWcVyyX
Simply uncompress the included files onto your Windows machine, then look for configuration instructions in the included README.txt. You’ll need to set the IP address of a Volumio system that you’d like to control.
We’ve tested this with Spotify and a recent release of Volumio on RPi.
Almost a month and a half since our trial release and no feedback yet??!! Did anyone have a chance to try it?
Try MS Windows? No thanks 
I would love to be able to control Volumio with my Google home setup. Choose it as a playback device in the Google home app.
I do understand people are afraid of the 'always listening thing" but for me, I have nothing to hide 
and an option to turn it on/off would be very sufficient. Besides that, how great it is that at least someone is listening when we speak 
I tried to start the app on my windows10 pc, but it says, that the software is not compatble with my system.
Regards
Beat
Hey CloudConstable,
the programme opened and I could see Viola moving a bit. Sadly she did not react to my voice. I entered the correct IP address and tried the German server (n=2) and n=1. I also changed the wake word from “Viola” to “computer”.
Windows’ sound settings show me that my Microphone is working. However I’m not a MyVolumio user. Is this necessary?
Best regards
Chillman
PS: I discovered this thread the day before yesterday and find it quite interesting. Will the goal be to run DjViola (without the animation) parallelly to Volumio on a Pi or would that be too much for the little machine?
Thanks for sharing!
Why on Windows and not directly on RPi running Volumio?
First time Volumion here. I was searching for this without much expectations but am glad that the project was already started. I for one feel that voice control is absolutely essential (for me 
) the future is smart homes. I am also pro privacy but I’m sure the there’s already some white paper out there with tech to allay the fears of big brother listening in?
In any case, how are we doing on the progress of this?
I want to come home and say “volumio play Bach on Spotify” along with all other basic commands. That would be sufficient.
That long time and nothing happened. Alexa project also stopped …
Are there any project remaining regarding voice control?
1 Like