WTF! You shouldn't hot-plug the hat on the Raspberry Pi! One wrong move/ping offset and you could let the smoke out. Even if everything is aligned correctly, you may not mate the, e.g., ground or other power pins in the right order and could cause excess currents to flow through signal pins into the Raspberry Pi GPIO connections.
@@Geekydrones There isn't a way to use these devices to play music on them. But if you wanted an interim solution, you could use the Alexa Media Player integration from HACS to create an automation that triggers using a voice command you define, and then have that Alexa Media Player Integration send a command to your echo to execute a silent command. It would still require the Amazon cloud, but you could mute the Echo so it wasn't listening. So the only cmmand passed would be the one you send through the automation.
Do you know I want to make something like this and now I finally got the right video I actually want to make home assistant like with the wake of word hey Jarvis or wake up Jarvis thank you very much for this amazing video love from India❤👋
This is exactly the guide I was looking for and it's less than 2 weeks old! Great timing. Everything is working beautifully. Now I'm going to add a small display and make a case to fit it all together. Thanks!
Good tutorial, the only thing I can see that should have been done is a ‘sudo apt upgrade’ after the first ‘sudo apt update’ to actually install the available updates. There were 44 available updates in your case that weren’t run.
The algorithms did. Never thought of getting myself a echo alternative, but here I am, since RUclips thought, you like tech, you will like this video :D
It also comes with built in spyware and built in stability issues, and it even has a built in licensing watcher that breaks your settings if you don't pay them 200$
Thank you for this complete tutorial! I like you don't take shortcuts and exeplain everything that is needed. We use the Echo almost exlcusively to play music spotify. I still looking for complete guide to replace that feature of the Echo. There a lot of things to take into consideration which I cannot oversee, like music assistant, spotify, sonos and usable intents. Would be great if you could do a video on that!
Excellent tutorial! Thanks. I decided to setup 4 of these and it can be tedious running all of these commands one by one so I created a one step script to do it all. I also wrote a shell menu that will allow you to manage services and wakewords.
Thank you! This was great! I followed a similar tutorial and was able to get everything up and running, and with ChatGPT as well. I'm able to control my lights via the Jarvis assistant. I'm trying to figure out how to get a response to come out my Google Home Speaker? I'm able to run control the ligths, but how do i get to play a response that is coming from ChatGPT to my Google Nest Speaker?
Never owned Amazon or Google stuff. No trust. For me, practical voice assistant is limited. Most of the time I can hit the light switch or tap on a tablet or such do do stuff. Now and then when I am in an awkward spot and need the light on, it will come in handy. Instead of having to crawl or whatever to get to the switch, tablet or whatever, just speak to have it turn on.
I use a combo of Home Assistant and Home Bridge for my setup, and I use Siri as my voice assistant. I mostly use Home Assistant to automate my retro console collection. For example, my SNES is connected to a smart socket, and the SNES's power switch is left in the on position, that way it's powered on anytime the smart socket is on. I then have a series of video switches and IR blasters handling all of the video stuff. Just say "Siri turn on Super Nintendo" and everything turns on, and switches inputs automatically. Couple that with an EverDrive, and wireless controllers, and it's like playing on a modern console. I currently have 19 game consoles automated in my setup.
For the speaker cloth, maybe something like another ring that fits inside the lid to hold it stretched in place. Similar to how an embroidery hoop works.
This is a good idea as the friction of the speaker cloth should keep the ring friction locked inside the enclosed as well. Although I would probably put some ring catches in the enclosure anyway.
FREE 3D printing at public libraries! Many have Maker Spaces/Idea Labs with 3D printers which will print ".stl" files. Since pre-pandemic, that's where I've been getting all my 3d print jobs done. AND, Jeff, thanks for giving me a kick in the @SS to get back into the HA voice control. I've tried with some success with a pi 3b+ or 4?. Currently want to get a ESP32-S3 board working. "Everything Smart Home" covered the latter in a video. I started on it, but, got side tracked. Either way, thanks for the great content as usual.
restarted couple times. Assist Preferred Pipeline does not have jarvis or nabu in it only home asst cloud slow and fast gpt and extended open ai. and Wake word doesn't work where do I look ?
I'm working on a video on how to do this. But you need to make sure you have the whisper add on installed and the open wake word add on installed. And if you want the local text to speech h you will need to install the piper add on. After those are installed there will be 3 integrations to add for whisper, open wake word and piper if you installed that one. After that they should be choices
Thank you very much for this! This is soo much better than the ESPHome device that I tried earlier. That one had so many buffering issues and didn't seem like it had the horse power to run the services. So your solution appears to be working flawlessly. One thing to mention, even if you don't have a speaker you can use the audio jack on the Respeaker 2 Mic Hat to connect an external speaker/mic system with it's own amp and higher quality audio, mic
So tonight I tested using a USB Audio/MIC headset that I use for my daily conferences and plugged this into my pi zero. I changed my Wyoming service to use "CARD=Seri,DEV=0" (Plantronics Blackwire 3220 Seri, USB Audio) for both audio and mic. Not only was the mic allot better than the built-in ones on the audio hat, but the speaker quality was much better too. I am thinking about getting a conference speakerphone to provide a higher quality mic and speaker experience... plus many of these conference speakers have a built-in mic mute button. Thoughts? Have you tried this?
You have been a wonderful companion in my home automation journey, i have gained everything i know from you. Recently i ran into an issue , i have a WH8960 Audio hat , this hat doesn't have on board led's for which i wish to add seperate leds on my raspberry Pi zero 2 w, since i am not so knowledgeable in this field, can you please help have this LED feed for me , it wold be fine if you suggest me here , or it will be best for entire community if you make a video or prove some written step by step guide to have this in action
Ordered the small speakers from your link and the plug didn't fit unfortunately. Its slightly too small for the Respeaker hat connector. I was able to force it in there though lol.
@@SlackerLabs it still works, it’s just that the pins on the Respeaker connector are slightly farther apart so the connector doesn’t quite go on well. I do have to thank you for the guide though. The step by step was very helpful!
Same issue. The Keyestudio ReSpeaker uses a JST XH2.54 connector whereas the Seed Studio ReSpeaker uses a JST 2.0 which is what the speakers you referenced are meant for. So while you can force it to work (not recommended!) you might want to update either the HAT or the speaker recommendation to match the connector types.
There are Printing services that will ship you your custom 3D print. You usually just email them the stl file with your setting preferences and they get back to you with lead time and total cost with shipping.
My pi zero w 2 just keeps hanging on the driver installs. At the make -j4 command (when running ./install.sh). I just get about 20 fullstops until the pi stops responding.
So I tried similar approach but different. Used vanilla esphome firmware with some config, attached microphone and used external speaker (mediaplayer from HA) for feedback. All works great, sound quality on big home speaker is great, but not speech to text. It’s slow (I have HA running on virtual machine on qnap, but it’s not overloaded) and unreliable. TTS locally works fine, but not STT. I see you are using cloud and that what makes the difference…
I've gone through so many of these types of videos only to find out they "depend" on some cloud service at the end that was set up and configured outside their "assistant" instructional video. Am I correct by saying this one requires another service? I got to the end where you had "Ok_Nabu" as the wake word, but you said you used "Jarvis"... both Nabu and Jarvis are additional add-ons?
It requires a local Assistant Pipeline setup in Home Assistant. In setting up that pipeline you decide which parts you use. This video setups up the Wyoming Satellite software with local wake word. So the Pi is running the the wake word detection, in my case I'm using "hey jarvis" as the wake word. Once the pi is triggered it sends the voice to the local assist pipeline. You can run faster-whisper on your Home Assistant as an add-on to handle speech to text, so your home assistant device decodes the speech into text, and then executes the command. Then for any response back you need a service that can do text to speech. I use the Nabu casea cloud, so that is the only cloud service I need. But you could run the piper add-on in home assistant to handle that and nothing would need the cloud. You dont even need local wake word on the pi. Your home assistant local assist pipeline can handle that.
Great video. Is it possibly to get Assist to act on an Yes and No? Like, an automation ask if I want lights in the kitchen. And I answer 'Yes', 'No'. Like the amazone alexa?
Very good guide, but im having ap roblem its always asking for two detections on HA, butl always givin error on ha on configuring, it there a way to redected the assistant?
Thank you! This thing is pretty sweet, but quite loud. Is there a way to adjust the volume? I'd love to be able to automate the volume to adjust at different times of the day.
Two main reasons: - I don't mind bricking a Google Home if I screw up. I got three of them used for like $30. - Some of the components you use are either extremely hard to come by outside of the US, or simply much more expensive. To expand on the latter: There are only like 4 or 5 sellers of RPi in Hungary. All of them are completely, 100% out of stock for all RPi Zero models. There are literally none availabe in the country. And even if they _were_ in stock, the price of the bundle you linked for $35, is actually ~$58 for us. I also checked some used sites, but no luck. They are just too niche to have a vibrant market-unlike Homes and Echos. Of course, I could import them myself. But that would make them even more expensive. This would easily become a $100 project just because of the Pi. And that's the thing, this isn't just about the brains, it's about every single part you use. Sure, you could most definitely find a suitable replacement I can buy here locally for a reasonable price, but _I_ can't. Most people who might be interested in doing this, can't. And if I get those exact things, then this is like a ~$300 project I'm looking at just because of all the shipping costs.
Uhg, this again. As with local whole home audio from the year before (another half abandoned idea), the year of the voice was a complete and utter waste. Unreliable as all get out. Thank goodness they're actually working on UX improvements now.
I'm not sure what you found to be unreliable. I'm building out commands for mine. I can now walk into a room. Say hey jarvis it's dark in here, and home assistant turns on the lights in the room I am in. And it's completely local. Well except the response back that it turned on the lights in insert room name. The response I'm using Nabu casa.
still don't know what the added value is of "the year of the voice". When all local, it's too slow, bad understanding words,... or you have to invest in more expensive hardware, invest more time to keep it working, ... The method with nabu casa cloud should be faster , but it's .... cloud based. Only to turn on a light???? My google assistant can do this too. It all makes HA more cumbersome,slower,
@@SlackerLabs so, you say 'it's dark in here's in order to turn on lights? And to open roller shutters? 'is's very dark'? It looks like creating a problem for a solution... I just say 'turn on lights', and they turn on. Don't need a complex setup for that.
@@StefanUytterhoeven I think the difference is the privacy aspect. Yep its slower when the entire pipeline is completely local. I have a video coming up that will show the difference in speed. Its always a balance of convivence and privacy. HA gives you more control of that slider. But each end of the spectrum comes with costs. I am not sure Google has the context for me to walk into a room and say turn on the lights, and it just turn on the lights in the room I am. Actually just tried it and it did't work. But that is functionality I built using the HA Voice Assistant. No LLM, no cloud required. I'm not sure there is another platform out there that can do that without using an LLM. But you are right. If Google gives you want you need then there is no value in adding in HA specific voice.
If I click on the link and then it take me to my HA and then says this: "This redirect is not supported by your Home Assistant installation. It needs either the Home Assistant Operating System or Home Assistant Supervised installation method. For more information, see the" and takes me to a link how to install HA. Is there a way to fix this?
It all most be easer if you could make a DD image to download. Then could set up your personal things. Like Wi-Fi and things. I been falling the step-by-step and got the hat with 2 mics but on the "Wyominig Satellite" Autodetect it can not find it. says you my have to restart it.
the big canister amazon echo fell from the counter a few days ago and broke the top off... I considered shooting it, but this is a better idea for its use.
Command prompt is basically the same as your command line on Mac putty is better then that because it adds features like saving a address and other stuff
It's not possible to use the Wyoming satellite at this point. Not sure it will eve actually. But if you have other speakers you use today and a streaming service connected to them you may be able to leverage those speakers. I'm working on a video to show that off. I have a command built that will play music in the room I'm in just by saying something like hey jarvis can I hear some classical music.
Yes, with the Ollama integration you can do this. I am using it on mine with great results. You need a lot of VRAM though for good performance. If you get bad results with the default Ollama profile, increase the context window size. This is particularly needed if you are exposing a lot of identities. Also you need a model that knows how to use tools. Qwen2.5 & Llama 3.1 work well. You'll want at least the 7-8b model sizes, the bigger the better. I run Qwen2.5 14b with 32k context. Even with nearly 100 exposed entities, it does a fantastic job.
I really enjoy your videos and particularly your sense of humor! Always provide a chuckle to two. Thank you for direction as this is something I am wanting to do but just haven't got around to it. Now I will.
just ordered the atoms ... now a decision to make.... which 3d printer your use? I am very insterest in printing my own if you can add the file for printing that would be great. I would also consider a whole kit and pay you for your work.
the links to two different ones I printed should be in the description now. I have an Ender 5 Pro. I added some better bed springs, a PEI build plate, and a better bed heater which heats more evenly.
@@SlackerLabs i have the CR10 and the PRUSA Minil. I hate the CR10 had a bunch of mods and it is still a pain to print with. The mini is sweet. Should I stay with the atoms or go with the PI Zero?
@@retirednowwhat4292 Thats a good question. My only issue with the Atoms is there doesn't seem to be an easy way to get a really good sounding speaker on there. If you can solve that in a way that is acceptable I think the Atoms might be a good choice. Especially now that Micro Wake Word is a thing, and the team is working hard to get more of this software on the ESP devices. I think the mics on the 2 mic hat have better pickup than the Atom Echo. But that ins't a fair comparison. Not a direct answer, but hopefully that helps with your thinking.
I built 4 of the ESP 32 versions. Once I buit 1 of the wyoming satellites, I trashed the 4 esp32 versions. The wyoming satellites with the Pi and 2 mic hat are just so much better and easier.
Question again. When I go into Home Assistant, under the Preferred Pipeline, I only see "Home Assistant". When I say "Hey Jarvis" the LED's light up but the Assist in progress doesn't change. Is it because I didn't name the Pi Zero "Jarvis-masterbedroom"? I named it "hass-echo-bdrm". Also, the LEDs stay lit up.
Can these be used as "media player" devices in HASS? It'd be awesome if, in addition to voice inputs and responses, it could also speak via a triggered automation.
They can't be as of yet. Perhaps down the road. I've been using the google homes for media player because I don't have to go through the google cloud. Can just stream to them over the local network.
I feel like still no one knows this so I post as part of my crusade: Windows 10+ has ssh as a native command from both CMD and powershell. you don't need putty anymore!
Wow, great video, thank you a lot @SlackerLabs ! What about power this device with a battery, directly connected to the raspberry pi internally, and let that be charged wiressly, for example? What is the best battery to choose to do this and also power the speaker correctly? Thank you!
Yep.. Pi zero w2 $20 Pi hat $10 Speaker $4 Sd card $8.50 And that's using Amazon this morning. You can't get the pi hat for $1.50 on aliexpress. But sure...doubled.
@@SlackerLabs rasp pi- $20ea, not including PSU header pins roughly $10 re-speaker to mic - $10 hammer jig $? 2pk SD card $14 speakers 4/$10 $64 +, not including tax, etx thats so far.... you claim less than $50 total.. and this is on the low end.. not sure how much the hammer jig cost, at this point, dont care.. youre a lil old to be butthurt about something as YOU giving incorrect prices.. and not everyone is willing to wait 3months to a year for alieexpress.. not when you can get an Echo dot gen 3 for $45 and its there in less than a week. have a wonderful day , Sir.
Nice - the option to use a separate speaker is what I was wondering before going into this video: I have a few Sonos Play 5s that I havent used in a while and wanted to upcycle, so this might do the trick - just gotta figure out how to power+mount the PI inside the enclosure of the device to make it look neat.
Thats a good point. You could totally use the audio jack and just plug that pi hat into any speaker that has the rca jack. I am going to try that with the Atom Echo, and will do an update video when I get that done.
@@SlackerLabs Gave it a try today since the parts arrived. On the video and screenshot on the guide, the OS image is listed as being the lite 64, but on the text of the guide it says legacy lite 64. For me this was important - the bookworm-based image failed to record any audio via arecord and the kernel logs had a bunch of errors related to initializing the hat's DAC (I've found similar complaints online); with the legacy/buster-based image, it works. (Seems this specific hat is considered unsupported/legacy :( ) Now to figure out why the commands seem to be dropped/ignored, even though the wakeword is handled, "assist in progress" turns on .. While text + microphone from my laptop works :/ Edit: I figured it out - turns out Assist doesn't like my Brazilian/English accent :P "Turn off main bedroom lights" got interpreted as "I don't have a better life", "Don't ask me, but I'll fight." and other silly interpretations 🤣🤣
Tried your code for using M5stack as the mic and GH mini as the speaker, it didn't work. Do I need to add scripts elsewhere other than the config and automation yaml?
You shouldn't. As long as that m5 is linked to a pipeline that should be it. If you are using the conversation and or internet script for the first time you would need to restart HA I think. Does it just say it doesn't understand when you try to use the sentence?
@@SlackerLabs No sir, the response still comes out of the atom and not my GH speaker. I do not understand why it fails to run. I'll re-upload the codes, run the automation, and check the logs. Can I message you through Discord the failure?
@@SlackerLabs I've tried this on two different setups and I cannot get even one of them to work..... NO fault of yours but I've been over this about 10 times and cannot get it working so I'm not really sure what comes next....
@@SlackerLabs pretty good! I use one of that round MH-ET mics in custom device in my bedroom - it picks me from across the room easily, and in 2 months it's there it had only couple of false-triggerings. ESP32-S3-BOX is also pretty good.
This is fantastic, and perfectly timed! I've been looking to make a similar project. What connectors did the speakers you bought have, in order to fit in your keyestudio ReSpeaker board? I want to make sure I get the right ones, to avoid the frustration of attaching new connectors.
Thanks for the guide! Using a different device for providing the response is a great idea, since I'll probably set up a multi-room audio solution anyway and then only need to add a few mics around the place. I'm guessing there's a way to re-route the response to a specific speaker based on the mic that pickes up the wakeword, even without explicitly providing an automation for each sentence?
Yes. I actually have a bit of jinja that grabs the last jarvis entity triggered, gets the room, then routes the output to a google home in that room. So I can walk around and ask it where am I, and it will always play in the room I am in and tell me the room.
even tho i use it myself, more out of habit than anything else: you dont need putty on windows anymore, you can just "ssh" inside of windows powershell!
So, I've built this before but ran into the issue of it crashing after a few hours. /var/log/messages doesn't really show anything. I don't know why it crashes all the time. Some things point to the SD card, but I tried a few. Going to get a more expensive one to see if that's the issue. There are also issues if you update the Pi.. that's a problem. You end up with a TON of errors.
First I want to say great video, I used it and built one of my own, thank you, next do you know how I can go about sending every voice command to mqtt? I was able to accomplish this using ESP32s but not sure how id go about doing that with this. can you help?
hmm. Thats a good question. I am not sure. I will have to look into that,. I was thinking of grabbing the command after faster-whisper decoded it, but right now it just stores it in the log. But I suspect it just needs a sensor set up to expose it.
Does the ReSpeaker require a separate power cable, or will it take power from the Raspberry Pi through the GPIO pins? I only see one power cable on the pictures (from Amazon or their site).
Wish I could have used your affiliate links but they don't work for the uk, thanks for the guide, loving it, and bringing me one step closer to getting rid of Alexa
thank you very much, im gonna try your alkthrough as others miss parts and then i get stuck at about C7.2 on your video. so im hoping your video walk thorigh helps more than others
What microphone do i buy i cant see any mention to the mic and how to install it. From myvreserch you use a respeaker but those are ove $100 making it a excessive project. Please correct me and let me know what mic to use
Nice, but all of this can be done via a one Bash script or Ansible playbook. Faster and easier. Besides this way you are sure that there are no errors and replacement in playbook or script can be done thanks awk or sed commands. Thanks this approach next time you will record shorter video. Time is money. Anyway I appreciate it. Cheers.
@@SlackerLabs that is why there are if else where you can add conditions. I always do this for each step and also log each step to a log file. It is just a matter of experience. I can write both script and ansible playbook if you want. For sure I will try to build this and I was thinking about connecting it to fabric and self hosted LLM.
My thought is the fabric stretches over the speaker grill and is glued with spray glue. Stretch the fabric to the bottom of the grill where it can't be seen. Give a little trim. Then a few magnets to hold the grill on or a screw from the bottom going into the grill. I bet making a little ring the entire grill could be shoved in(holds the fabric on while stretching) would also look pretty good. I might make it a second color to give a little accent.
@@SlackerLabs Did the whole tutorial with no mic board because I'm still waiting on it. Amazon is late. 😢 Here's hoping I didn't mess up because I obviously couldn't test it along the way. 😆 I had a really strange problem though. I can't get WiFi to connect so I got an ethernet adapter plugged in. I tried two different PI Zero W 2 boards and flashed the card using PI imager from both Linux and Windows. I'm starting to wonder if there's a bug in the 2024-07-04-raspios-bookworm-arm64-lite build. I'll have to test another PI OS to see if I somehow got multiple bad boards. Quadruple checked SSID and password settings.
@@SlackerLabs I dropped the WiFi(wlan0 down) and turned it back on(wlan0 up). I also tried to enter creds from the raspi config option. That let me enter SSID and password but it wouldn't accept them. I'm going to burn a different image to test the boards right now.
For those who have never set up a voice assistant in HA, first follow the steps on the HA support url under "voice_control" and "Installing a local assistant pipeline". I couldn't figure out why after all the steps I followed, my assistant would not respond or hear the wake word.
It wouldn't hear the wake word without the pipeline? It should hear the wake word but wouldn't be able to send the data anywhere without the pipeline. I will have to double check.
@@SlackerLabs The RP heard it... as I could get the LEDs to respond, but within HA, it would not detect it (Assist in Progress). It all worked after installing piper, whisper in HA. I'm not sure which one did it, but, after that... success. Also the LEDs didn't respond correctly (they'd turn on, but not off). After the above, it worked and HA responded. I did the install of all your steps probably 3 or 4 times (very well organized.. and well done! thank you!). I also followed the steps directly from the wyoming github site too just to get more familiar with everything :)
Got it running but it's definitely a bit slow right now and need to get it to be a bit faster to be a viable replacement for all house devices. Will try to figure out how to speed it up. Not sure the best options for that but thinking out loud: - Using a more beefy raspberry pi (v4 or v5) - Sourcing open wake word to the HA server - Sourcing the open wake word to PC with GPU
@@VACInc I have noticed using home assistant cloud to the stt is slightly faster than using faster whisper. But if ha was running on faster hardware locally it should be faster n
Wow this is the 4th time reinstalling it. The sound test works but when I get to the step C12.1 it never shows up in my Home Assistant. It looks just like your video up to then. I got home Assistant that came installed on a ZimaBlade with CasaOS Not sure if that is why it's not showing up.
@@SlackerLabs Can put my Home Assistant link in the web page you link to and it takes me to this on my Home Assistant "This redirect is not supported by your Home Assistant installation. It needs either the Home Assistant Operating System or Home Assistant Supervised installation method. For more information, see the documentation." Guess I need to copy and paste some script some were in Home Assistant or on the command line get a Host* and port* that it ask me for when I try and add Wyoming Protocol
This just seems way too complicated I've been working on it for 3 days best I know now I think I have to put some script someplace and the home assistant but I just don't know where to copy and
Just wanted to test on installing one part whisper. So on the command line were my home assistant is installed ran in to all sort of problems. root@casaos:~# pip install -U openai-whisper -bash: pip: command not found root@casaos:~# apt install pip Reading package lists... Done Building dependency tree... Done Reading state information... Done Note, selecting 'python3-pip' instead of 'pip' Some packages could not be installed. This may mean that you have requested an impossible situation or if you are using the unstable distribution that some required packages have not yet been created or been moved out of Incoming. The following information may help to resolve the situation: The following packages have unmet dependencies: python3-distutils : Depends: python3:any (< 3.10) Depends: python3-lib2to3 (= 3.9.2-1) but it is not going to be installed python3-setuptools : Depends: python3-pkg-resources (= 52.0.0-4) but 66.1.1-1 is to be installed E: Unable to correct problems, you have held broken packages. root@casaos:~# They need to make this easier.
WTF! You shouldn't hot-plug the hat on the Raspberry Pi! One wrong move/ping offset and you could let the smoke out. Even if everything is aligned correctly, you may not mate the, e.g., ground or other power pins in the right order and could cause excess currents to flow through signal pins into the Raspberry Pi GPIO connections.
Important safety tip.
How else am I supposed to light my Pi? I’m addicted to smoking Pi. 😙💨😶🌫️
We use our echo to play amazon music. Any thoughts on how one would integrate, or be able to do this. I also use nabacasa
@@Geekydrones There isn't a way to use these devices to play music on them. But if you wanted an interim solution, you could use the Alexa Media Player integration from HACS to create an automation that triggers using a voice command you define, and then have that Alexa Media Player Integration send a command to your echo to execute a silent command.
It would still require the Amazon cloud, but you could mute the Echo so it wasn't listening. So the only cmmand passed would be the one you send through the automation.
@@SlackerLabs aww true.. nice workaround. Appreciate you
Do you know I want to make something like this and now I finally got the right video I actually want to make home assistant like with the wake of word hey Jarvis or wake up Jarvis thank you very much for this amazing video love from India❤👋
This is exactly the guide I was looking for and it's less than 2 weeks old! Great timing. Everything is working beautifully. Now I'm going to add a small display and make a case to fit it all together. Thanks!
Good tutorial, the only thing I can see that should have been done is a ‘sudo apt upgrade’ after the first ‘sudo apt update’ to actually install the available updates. There were 44 available updates in your case that weren’t run.
This is by far one of the best guides available right now. Let's hope the algorithm blesses you!
The algorithms did. Never thought of getting myself a echo alternative, but here I am, since RUclips thought, you like tech, you will like this video :D
Is harder in Windows to do ssh, you start an app called Terminal and typ ssh, o is that not the same name in MacOS? 😀, Thank for a nice Guide !!!
For those who don't know, Windows already comes with built-in SSH, from OpenSSH
It also comes with built in spyware and built in stability issues, and it even has a built in licensing watcher that breaks your settings if you don't pay them 200$
Thank you for this complete tutorial! I like you don't take shortcuts and exeplain everything that is needed. We use the Echo almost exlcusively to play music spotify. I still looking for complete guide to replace that feature of the Echo. There a lot of things to take into consideration which I cannot oversee, like music assistant, spotify, sonos and usable intents. Would be great if you could do a video on that!
I use my Echo for the same. I'm waiting for some cool integration in HomeAssistant after which I can completely get rid of my echo.
Excellent tutorial! Thanks. I decided to setup 4 of these and it can be tedious running all of these commands one by one so I created a one step script to do it all. I also wrote a shell menu that will allow you to manage services and wakewords.
Thank you! This was great! I followed a similar tutorial and was able to get everything up and running, and with ChatGPT as well. I'm able to control my lights via the Jarvis assistant. I'm trying to figure out how to get a response to come out my Google Home Speaker? I'm able to run control the ligths, but how do i get to play a response that is coming from ChatGPT to my Google Nest Speaker?
Never owned Amazon or Google stuff. No trust. For me, practical voice assistant is limited. Most of the time I can hit the light switch or tap on a tablet or such do do stuff. Now and then when I am in an awkward spot and need the light on, it will come in handy. Instead of having to crawl or whatever to get to the switch, tablet or whatever, just speak to have it turn on.
I use a combo of Home Assistant and Home Bridge for my setup, and I use Siri as my voice assistant. I mostly use Home Assistant to automate my retro console collection. For example, my SNES is connected to a smart socket, and the SNES's power switch is left in the on position, that way it's powered on anytime the smart socket is on. I then have a series of video switches and IR blasters handling all of the video stuff. Just say "Siri turn on Super Nintendo" and everything turns on, and switches inputs automatically. Couple that with an EverDrive, and wireless controllers, and it's like playing on a modern console. I currently have 19 game consoles automated in my setup.
How do you get Siri to work on speakers around the house without Internet?
For the speaker cloth, maybe something like another ring that fits inside the lid to hold it stretched in place. Similar to how an embroidery hoop works.
This is a good idea as the friction of the speaker cloth should keep the ring friction locked inside the enclosed as well. Although I would probably put some ring catches in the enclosure anyway.
I have Sonos speakers in many of my rooms, and I would like to use them as the speaker output for the Wyoming devices. Any pointers?
FREE 3D printing at public libraries! Many have Maker Spaces/Idea Labs with 3D printers which will print ".stl" files. Since pre-pandemic, that's where I've been getting all my 3d print jobs done. AND, Jeff, thanks for giving me a kick in the @SS to get back into the HA voice control. I've tried with some success with a pi 3b+ or 4?. Currently want to get a ESP32-S3 board working. "Everything Smart Home" covered the latter in a video. I started on it, but, got side tracked. Either way, thanks for the great content as usual.
I threw my GFs Alexa away. She has no idea where it is.
a nice way to ditch my cia controlled alexa
I feel like your view & sub counts are lower than they should be.
Me too. Haha. Me too. RUclips. Just a weird beast.
Could you provide a link to speakers with the right connector for the respeaker board? The one you linked has a connector that doesn't fit
Speed 1.75. You're welcome.
restarted couple times. Assist Preferred Pipeline does not have jarvis or nabu in it only home asst cloud slow and fast gpt and extended open ai. and Wake word doesn't work where do I look ?
I'm working on a video on how to do this. But you need to make sure you have the whisper add on installed and the open wake word add on installed. And if you want the local text to speech h you will need to install the piper add on.
After those are installed there will be 3 integrations to add for whisper, open wake word and piper if you installed that one.
After that they should be choices
@@SlackerLabs like a champ. Thanks
This is a great projet but the process is way to complicated, this is something that hopefully home assistant is working on.
It is.
Windows 11 has built in "Windows PowerShell" can use it and not putty. In they just type "ssh name@ip"
Super cool but I have so many projects on the go already so will wait for the nabu casa hardware.
I get what you're saying. There is an abundance of home automation projects that are cool enough to build.
Thank you very much for this! This is soo much better than the ESPHome device that I tried earlier. That one had so many buffering issues and didn't seem like it had the horse power to run the services. So your solution appears to be working flawlessly. One thing to mention, even if you don't have a speaker you can use the audio jack on the Respeaker 2 Mic Hat to connect an external speaker/mic system with it's own amp and higher quality audio, mic
So tonight I tested using a USB Audio/MIC headset that I use for my daily conferences and plugged this into my pi zero. I changed my Wyoming service to use "CARD=Seri,DEV=0" (Plantronics Blackwire 3220 Seri, USB Audio) for both audio and mic. Not only was the mic allot better than the built-in ones on the audio hat, but the speaker quality was much better too. I am thinking about getting a conference speakerphone to provide a higher quality mic and speaker experience... plus many of these conference speakers have a built-in mic mute button. Thoughts? Have you tried this?
@@MyBluettiif the usb speakerphone will be detected by alsa (most will work in Linux but not all) you can use anything.
You have been a wonderful companion in my home automation journey, i have gained everything i know from you.
Recently i ran into an issue , i have a WH8960 Audio hat , this hat doesn't have on board led's for which i wish to add seperate leds on my raspberry Pi zero 2 w, since i am not so knowledgeable in this field, can you please help have this LED feed for me , it wold be fine if you suggest me here , or it will be best for entire community if you make a video or prove some written step by step guide to have this in action
Ordered the small speakers from your link and the plug didn't fit unfortunately. Its slightly too small for the Respeaker hat connector. I was able to force it in there though lol.
Really? Hmmm.
@@SlackerLabs it still works, it’s just that the pins on the Respeaker connector are slightly farther apart so the connector doesn’t quite go on well. I do have to thank you for the guide though. The step by step was very helpful!
Same issue. The Keyestudio ReSpeaker uses a JST XH2.54 connector whereas the Seed Studio ReSpeaker uses a JST 2.0 which is what the speakers you referenced are meant for. So while you can force it to work (not recommended!) you might want to update either the HAT or the speaker recommendation to match the connector types.
You don't need to type "apt-get" any more. The update command is simply "sudo apt update"
6:45 lol, "That's what Paul said"... that is exactly what I was thinking when you said that. I heard Paul's high-pitched quivering "oh yeaaaah"
On the Windows PC, you can just open a command prompt and use that for SSH. No need to install Putty
Command prompt? I think you need to use Powershell, right? Or maybe Microsoft made that possible in CMD now?
@@joe-skeen
No, I just use ssh from the command line
*you* could, but not everyone is as technical inclined. It's a guide for everyone.
@@Preske
I was just saying that you don't need to install putty. The same commands he's using work on Windows command prompt.
Yeah, I couldn't remember if it was a command or powershell on windows.
Please consider selling the enclosures. I don't have the room or the budget for 3d printing at the moment.
Love your videos.
There are Printing services that will ship you your custom 3D print. You usually just email them the stl file with your setting preferences and they get back to you with lead time and total cost with shipping.
My pi zero w 2 just keeps hanging on the driver installs. At the make -j4 command (when running ./install.sh). I just get about 20 fullstops until the pi stops responding.
So I am wondering if you can take and put that. I'm like a ceiling speaker at all and and if it would be able to power it
I don't see why you wouldn't be able to do that
I subscribe two days ago when you first announced that you were going to do this. Happy I did!
So I tried similar approach but different. Used vanilla esphome firmware with some config, attached microphone and used external speaker (mediaplayer from HA) for feedback. All works great, sound quality on big home speaker is great, but not speech to text. It’s slow (I have HA running on virtual machine on qnap, but it’s not overloaded) and unreliable. TTS locally works fine, but not STT. I see you are using cloud and that what makes the difference…
It might. The STT using Nabu Casa is really good. I have pretty much switched over to using it.
I like your T-shirt! ... and your content too :)
Hit a wall at Step 10 record a test (C10.1)
I'm getting the error arecord: set_params:1416: Unable to install hw params:
Anyone else run into this?
I've gone through so many of these types of videos only to find out they "depend" on some cloud service at the end that was set up and configured outside their "assistant" instructional video. Am I correct by saying this one requires another service? I got to the end where you had "Ok_Nabu" as the wake word, but you said you used "Jarvis"... both Nabu and Jarvis are additional add-ons?
It requires a local Assistant Pipeline setup in Home Assistant. In setting up that pipeline you decide which parts you use. This video setups up the Wyoming Satellite software with local wake word. So the Pi is running the the wake word detection, in my case I'm using "hey jarvis" as the wake word. Once the pi is triggered it sends the voice to the local assist pipeline. You can run faster-whisper on your Home Assistant as an add-on to handle speech to text, so your home assistant device decodes the speech into text, and then executes the command. Then for any response back you need a service that can do text to speech. I use the Nabu casea cloud, so that is the only cloud service I need. But you could run the piper add-on in home assistant to handle that and nothing would need the cloud.
You dont even need local wake word on the pi. Your home assistant local assist pipeline can handle that.
Great video just great, gonna copy it and make my own wyoming satellite now :D
Thanks Slacker Labs
Great video. Is it possibly to get Assist to act on an Yes and No?
Like, an automation ask if I want lights in the kitchen. And I answer 'Yes', 'No'. Like the amazone alexa?
Not yet. At least that I know off. No way to have it trigger and listen in response.
Excellent video. One question from me though. Will this work with a normal Pi Zero W or must it be a Pi Zero 2 W? Thanks for your help.
Very good guide, but im having ap roblem its always asking for two detections on HA, butl always givin error on ha on configuring, it there a way to redected the assistant?
Thank you! This thing is pretty sweet, but quite loud. Is there a way to adjust the volume? I'd love to be able to automate the volume to adjust at different times of the day.
Works great, thanks for this video. I have only one problem: The volume of the speaker is much to loud. Is there a way to turn it down?
What I would want much rather than a separate ~50 investment is a way to turn an Echo (or a Google Home in my case) into such a speaker.
Two main reasons:
- I don't mind bricking a Google Home if I screw up. I got three of them used for like $30.
- Some of the components you use are either extremely hard to come by outside of the US, or simply much more expensive.
To expand on the latter:
There are only like 4 or 5 sellers of RPi in Hungary.
All of them are completely, 100% out of stock for all RPi Zero models. There are literally none availabe in the country.
And even if they _were_ in stock, the price of the bundle you linked for $35, is actually ~$58 for us.
I also checked some used sites, but no luck. They are just too niche to have a vibrant market-unlike Homes and Echos.
Of course, I could import them myself. But that would make them even more expensive. This would easily become a $100 project just because of the Pi.
And that's the thing, this isn't just about the brains, it's about every single part you use. Sure, you could most definitely find a suitable replacement I can buy here locally for a reasonable price, but _I_ can't. Most people who might be interested in doing this, can't.
And if I get those exact things, then this is like a ~$300 project I'm looking at just because of all the shipping costs.
Uhg, this again. As with local whole home audio from the year before (another half abandoned idea), the year of the voice was a complete and utter waste. Unreliable as all get out.
Thank goodness they're actually working on UX improvements now.
I'm not sure what you found to be unreliable. I'm building out commands for mine. I can now walk into a room. Say hey jarvis it's dark in here, and home assistant turns on the lights in the room I am in. And it's completely local. Well except the response back that it turned on the lights in insert room name. The response I'm using Nabu casa.
still don't know what the added value is of "the year of the voice". When all local, it's too slow, bad understanding words,... or you have to invest in more expensive hardware, invest more time to keep it working, ... The method with nabu casa cloud should be faster , but it's .... cloud based.
Only to turn on a light???? My google assistant can do this too. It all makes HA more cumbersome,slower,
@@SlackerLabs so, you say 'it's dark in here's in order to turn on lights? And to open roller shutters? 'is's very dark'? It looks like creating a problem for a solution... I just say 'turn on lights', and they turn on. Don't need a complex setup for that.
@@StefanUytterhoeven I think the difference is the privacy aspect. Yep its slower when the entire pipeline is completely local. I have a video coming up that will show the difference in speed.
Its always a balance of convivence and privacy. HA gives you more control of that slider. But each end of the spectrum comes with costs.
I am not sure Google has the context for me to walk into a room and say turn on the lights, and it just turn on the lights in the room I am. Actually just tried it and it did't work. But that is functionality I built using the HA Voice Assistant. No LLM, no cloud required. I'm not sure there is another platform out there that can do that without using an LLM.
But you are right. If Google gives you want you need then there is no value in adding in HA specific voice.
So you're not using any amplifier for the speaker? That sound is solely coming from the ReSpeaker output?
Correct. It's just running off that respeaker.
If I click on the link and then it take me to my HA and then says this: "This redirect is not supported by your Home Assistant installation. It needs either the Home Assistant Operating System or Home Assistant Supervised installation method. For more information, see the" and takes me to a link how to install HA. Is there a way to fix this?
It all most be easer if you could make a DD image to download. Then could set up your personal things. Like Wi-Fi and things. I been falling the step-by-step and got the hat with 2 mics but on the "Wyominig Satellite" Autodetect it can not find it. says you my have to restart it.
I think I may need to get that shir
the big canister amazon echo fell from the counter a few days ago and broke the top off... I considered shooting it, but this is a better idea for its use.
Whoa...Nice!
Great tutorial! Real copy/paste. 😀👍
Command prompt is basically the same as your command line on Mac putty is better then that because it adds features like saving a address and other stuff
Is it possible to play music off these speakers? And can they be put into groups if they can play music?
It's not possible to use the Wyoming satellite at this point. Not sure it will eve actually.
But if you have other speakers you use today and a streaming service connected to them you may be able to leverage those speakers.
I'm working on a video to show that off. I have a command built that will play music in the room I'm in just by saying something like hey jarvis can I hear some classical music.
what are your settings in the voice assistant under activation word? because under step 22 i get no reaktion, no matter what word i use.
is it possible to connect local LLMs like llama to it?
Yes, with the Ollama integration you can do this. I am using it on mine with great results. You need a lot of VRAM though for good performance. If you get bad results with the default Ollama profile, increase the context window size. This is particularly needed if you are exposing a lot of identities. Also you need a model that knows how to use tools. Qwen2.5 & Llama 3.1 work well. You'll want at least the 7-8b model sizes, the bigger the better. I run Qwen2.5 14b with 32k context. Even with nearly 100 exposed entities, it does a fantastic job.
Question. WIll this work with a Pi Zero v 1.1 or does it have to be a Pi Zero 2W?
I really enjoy your videos and particularly your sense of humor! Always provide a chuckle to two.
Thank you for direction as this is something I am wanting to do but just haven't got around to it. Now I will.
just ordered the atoms ... now a decision to make.... which 3d printer your use? I am very insterest in printing my own if you can add the file for printing that would be great. I would also consider a whole kit and pay you for your work.
the links to two different ones I printed should be in the description now. I have an Ender 5 Pro. I added some better bed springs, a PEI build plate, and a better bed heater which heats more evenly.
@@SlackerLabs i have the CR10 and the PRUSA Minil. I hate the CR10 had a bunch of mods and it is still a pain to print with. The mini is sweet. Should I stay with the atoms or go with the PI Zero?
@@retirednowwhat4292 Thats a good question. My only issue with the Atoms is there doesn't seem to be an easy way to get a really good sounding speaker on there. If you can solve that in a way that is acceptable I think the Atoms might be a good choice. Especially now that Micro Wake Word is a thing, and the team is working hard to get more of this software on the ESP devices. I think the mics on the 2 mic hat have better pickup than the Atom Echo. But that ins't a fair comparison.
Not a direct answer, but hopefully that helps with your thinking.
I built 4 of the ESP 32 versions. Once I buit 1 of the wyoming satellites, I trashed the 4 esp32 versions. The wyoming satellites with the Pi and 2 mic hat are just so much better and easier.
Would there also be a way to include bluetooth tracking on this device?
Question again. When I go into Home Assistant, under the Preferred Pipeline, I only see "Home Assistant". When I say "Hey Jarvis" the LED's light up but the Assist in progress doesn't change. Is it because I didn't name the Pi Zero "Jarvis-masterbedroom"? I named it "hass-echo-bdrm". Also, the LEDs stay lit up.
First
any chance it would work with a zero w? have one sitting around I don't know what to do with
Can these be used as "media player" devices in HASS? It'd be awesome if, in addition to voice inputs and responses, it could also speak via a triggered automation.
They can't be as of yet. Perhaps down the road. I've been using the google homes for media player because I don't have to go through the google cloud. Can just stream to them over the local network.
@@SlackerLabsIs there a tutorial for this?
I feel like still no one knows this so I post as part of my crusade: Windows 10+ has ssh as a native command from both CMD and powershell. you don't need putty anymore!
Wow, great video, thank you a lot @SlackerLabs !
What about power this device with a battery, directly connected to the raspberry pi internally, and let that be charged wiressly, for example? What is the best battery to choose to do this and also power the speaker correctly? Thank you!
Is there by any chance a way to adjust the output volume ?
can you use a pi 4? or a pi zero w? i have both those on hand.
Get back to life? Life is overrated. HomeAssistant is the best🤣!!!
i stopped watching when the " for less than $50" was doubled . 3m34s into the vid.
Yep..
Pi zero w2 $20
Pi hat $10
Speaker $4
Sd card $8.50
And that's using Amazon this morning. You can't get the pi hat for $1.50 on aliexpress.
But sure...doubled.
@@SlackerLabs
rasp pi- $20ea, not including PSU
header pins roughly $10
re-speaker to mic - $10
hammer jig $?
2pk SD card $14
speakers 4/$10
$64 +, not including tax, etx
thats so far.... you claim less than $50 total.. and this is on the low end.. not sure how much the hammer jig cost, at this point, dont care.. youre a lil old to be butthurt about something as YOU giving incorrect prices.. and not everyone is willing to wait 3months to a year for alieexpress.. not when you can get an Echo dot gen 3 for $45 and its there in less than a week. have a wonderful day , Sir.
can i use the bluetooth microphone for this project?
Nice - the option to use a separate speaker is what I was wondering before going into this video: I have a few Sonos Play 5s that I havent used in a while and wanted to upcycle, so this might do the trick - just gotta figure out how to power+mount the PI inside the enclosure of the device to make it look neat.
Thats a good point. You could totally use the audio jack and just plug that pi hat into any speaker that has the rca jack. I am going to try that with the Atom Echo, and will do an update video when I get that done.
@@SlackerLabs Gave it a try today since the parts arrived. On the video and screenshot on the guide, the OS image is listed as being the lite 64, but on the text of the guide it says legacy lite 64. For me this was important - the bookworm-based image failed to record any audio via arecord and the kernel logs had a bunch of errors related to initializing the hat's DAC (I've found similar complaints online); with the legacy/buster-based image, it works. (Seems this specific hat is considered unsupported/legacy :( )
Now to figure out why the commands seem to be dropped/ignored, even though the wakeword is handled, "assist in progress" turns on .. While text + microphone from my laptop works :/
Edit: I figured it out - turns out Assist doesn't like my Brazilian/English accent :P "Turn off main bedroom lights" got interpreted as "I don't have a better life", "Don't ask me, but I'll fight." and other silly interpretations 🤣🤣
No need to use PuTTy on Windows for this. Windows has terminal and also PowerShell where the command lines that were used in the video can be used.
Tried your code for using M5stack as the mic and GH mini as the speaker, it didn't work. Do I need to add scripts elsewhere other than the config and automation yaml?
You shouldn't. As long as that m5 is linked to a pipeline that should be it. If you are using the conversation and or internet script for the first time you would need to restart HA I think.
Does it just say it doesn't understand when you try to use the sentence?
@@SlackerLabs No sir, the response still comes out of the atom and not my GH speaker. I do not understand why it fails to run. I'll re-upload the codes, run the automation, and check the logs. Can I message you through Discord the failure?
@the.kingant yes. I'll be online in a couple of hours. And yea. Make sure the automation is getting triggered.
This is really an awesome project!!! Missing one thing to make it perfect... Thank you so much for all your hard work and sharing!!! :)
Oh. Crap.
They are there now...
@@SlackerLabs Been there done that myself!! LOL Thank you so much!!
@@SlackerLabs I've tried this on two different setups and I cannot get even one of them to work..... NO fault of yours but I've been over this about 10 times and cannot get it working so I'm not really sure what comes next....
What is going on? Did the software go in the pi ok?
I have this one, and also couple of ESP32-S3 based. I like latter more, since they're cheaper, smaller and easier to configure. :)
How well does the mic work?
@@SlackerLabs pretty good! I use one of that round MH-ET mics in custom device in my bedroom - it picks me from across the room easily, and in 2 months it's there it had only couple of false-triggerings. ESP32-S3-BOX is also pretty good.
@@formatBCEgot a link to that setup?
I use tiny drop of BluTac for that cover.
Oh. Good suggestion!
This is fantastic, and perfectly timed! I've been looking to make a similar project.
What connectors did the speakers you bought have, in order to fit in your keyestudio ReSpeaker board? I want to make sure I get the right ones, to avoid the frustration of attaching new connectors.
Thanks for the guide! Using a different device for providing the response is a great idea, since I'll probably set up a multi-room audio solution anyway and then only need to add a few mics around the place. I'm guessing there's a way to re-route the response to a specific speaker based on the mic that pickes up the wakeword, even without explicitly providing an automation for each sentence?
Yes. I actually have a bit of jinja that grabs the last jarvis entity triggered, gets the room, then routes the output to a google home in that room. So I can walk around and ask it where am I, and it will always play in the room I am in and tell me the room.
how did he continue winning the elections repeatedly from 2013?
even tho i use it myself, more out of habit than anything else: you dont need putty on windows anymore, you can just "ssh" inside of windows powershell!
No need for putty on modern windows. It should have ssh built in or the ability to enable that feature.
AWESOME VIDEO! Thank you! Can it be ran on a virtual machine or an ESP32?
So, I've built this before but ran into the issue of it crashing after a few hours. /var/log/messages doesn't really show anything. I don't know why it crashes all the time. Some things point to the SD card, but I tried a few. Going to get a more expensive one to see if that's the issue.
There are also issues if you update the Pi.. that's a problem. You end up with a TON of errors.
I have not seen that yet. But I will be on the look out for it
Worked prefect gained a Sub
First I want to say great video, I used it and built one of my own, thank you,
next do you know how I can go about sending every voice command to mqtt?
I was able to accomplish this using ESP32s but not sure how id go about doing that with this. can you help?
hmm. Thats a good question. I am not sure. I will have to look into that,. I was thinking of grabbing the command after faster-whisper decoded it, but right now it just stores it in the log. But I suspect it just needs a sensor set up to expose it.
Does the ReSpeaker require a separate power cable, or will it take power from the Raspberry Pi through the GPIO pins? I only see one power cable on the pictures (from Amazon or their site).
It does not. It just used power off the pi
This hasn't been updated yet has it?
Wish I could have used your affiliate links but they don't work for the uk, thanks for the guide, loving it, and bringing me one step closer to getting rid of Alexa
thank you very much, im gonna try your alkthrough as others miss parts and then i get stuck at about C7.2 on your video. so im hoping your video walk thorigh helps more than others
What microphone do i buy i cant see any mention to the mic and how to install it. From myvreserch you use a respeaker but those are ove $100 making it a excessive project. Please correct me and let me know what mic to use
You can do this locally with assist microphone add on and a cheap usb conference speaker!
Great video, with the copy paste numbered code from your website. Top notch guide!
Is there a way to make a echo show?
Thank you so much for sharing this awesome project!
Nice, but all of this can be done via a one Bash script or Ansible playbook. Faster and easier. Besides this way you are sure that there are no errors and replacement in playbook or script can be done thanks awk or sed commands. Thanks this approach next time you will record shorter video. Time is money. Anyway I appreciate it. Cheers.
Yeah, no doubt. I considered doing a single script. but if something went wrong along the way, most people would have struggled to figure out where.
@@SlackerLabs that is why there are if else where you can add conditions. I always do this for each step and also log each step to a log file. It is just a matter of experience. I can write both script and ansible playbook if you want. For sure I will try to build this and I was thinking about connecting it to fabric and self hosted LLM.
@sysadmin-info that's a good idea. I will play around with that and see if I can make something as well.
Windows has WSL :)
My thought is the fabric stretches over the speaker grill and is glued with spray glue. Stretch the fabric to the bottom of the grill where it can't be seen. Give a little trim. Then a few magnets to hold the grill on or a screw from the bottom going into the grill. I bet making a little ring the entire grill could be shoved in(holds the fabric on while stretching) would also look pretty good. I might make it a second color to give a little accent.
I thought about the magnets. I feel like the top edge of this enclosure could be a bit taller. The top might in a bit better.
@@SlackerLabs Did the whole tutorial with no mic board because I'm still waiting on it. Amazon is late. 😢 Here's hoping I didn't mess up because I obviously couldn't test it along the way. 😆
I had a really strange problem though. I can't get WiFi to connect so I got an ethernet adapter plugged in. I tried two different PI Zero W 2 boards and flashed the card using PI imager from both Linux and Windows. I'm starting to wonder if there's a bug in the 2024-07-04-raspios-bookworm-arm64-lite build. I'll have to test another PI OS to see if I somehow got multiple bad boards. Quadruple checked SSID and password settings.
@jmr oh. That is weird. I think there is a command to do it from the OS. I I'll have to find it.
@@SlackerLabs I dropped the WiFi(wlan0 down) and turned it back on(wlan0 up). I also tried to enter creds from the raspi config option. That let me enter SSID and password but it wouldn't accept them. I'm going to burn a different image to test the boards right now.
@@jmr yea. Totally weird
For those who have never set up a voice assistant in HA, first follow the steps on the HA support url under "voice_control" and "Installing a local assistant pipeline". I couldn't figure out why after all the steps I followed, my assistant would not respond or hear the wake word.
It wouldn't hear the wake word without the pipeline? It should hear the wake word but wouldn't be able to send the data anywhere without the pipeline.
I will have to double check.
@@SlackerLabs The RP heard it... as I could get the LEDs to respond, but within HA, it would not detect it (Assist in Progress). It all worked after installing piper, whisper in HA. I'm not sure which one did it, but, after that... success. Also the LEDs didn't respond correctly (they'd turn on, but not off). After the above, it worked and HA responded. I did the install of all your steps probably 3 or 4 times (very well organized.. and well done! thank you!). I also followed the steps directly from the wyoming github site too just to get more familiar with everything :)
Got it running but it's definitely a bit slow right now and need to get it to be a bit faster to be a viable replacement for all house devices. Will try to figure out how to speed it up. Not sure the best options for that but thinking out loud:
- Using a more beefy raspberry pi (v4 or v5)
- Sourcing open wake word to the HA server
- Sourcing the open wake word to PC with GPU
After using it for a minute it seems to have sped up itself? Much better now. Definitely livable
@@VACInc I have noticed using home assistant cloud to the stt is slightly faster than using faster whisper. But if ha was running on faster hardware locally it should be faster n
Wow this is the 4th time reinstalling it. The sound test works but when I get to the step C12.1 it never shows up in my Home Assistant. It looks just like your video up to then.
I got home Assistant that came installed on a ZimaBlade with CasaOS Not sure if that is why it's not showing up.
Do you have the Wyoming integration installed? That is what should do the auto detection. www.home-assistant.io/integrations/wyoming
@@SlackerLabs Can put my Home Assistant link in the web page you link to and it takes me to this on my Home Assistant "This redirect is not supported by your Home Assistant installation. It needs either the Home Assistant Operating System or Home Assistant Supervised installation method. For more information, see the documentation." Guess I need to copy and paste some script some were in Home Assistant or on the command line get a Host* and port* that it ask me for when I try and add Wyoming Protocol
This just seems way too complicated I've been working on it for 3 days best I know now I think I have to put some script someplace and the home assistant but I just don't know where to copy and
Just wanted to test on installing one part whisper. So on the command line were my home assistant is installed ran in to all sort of problems.
root@casaos:~# pip install -U openai-whisper
-bash: pip: command not found
root@casaos:~# apt install pip
Reading package lists... Done
Building dependency tree... Done
Reading state information... Done
Note, selecting 'python3-pip' instead of 'pip'
Some packages could not be installed. This may mean that you have
requested an impossible situation or if you are using the unstable
distribution that some required packages have not yet been created
or been moved out of Incoming.
The following information may help to resolve the situation:
The following packages have unmet dependencies:
python3-distutils : Depends: python3:any (< 3.10)
Depends: python3-lib2to3 (= 3.9.2-1) but it is not going to be installed
python3-setuptools : Depends: python3-pkg-resources (= 52.0.0-4) but 66.1.1-1 is to be installed
E: Unable to correct problems, you have held broken packages.
root@casaos:~#
They need to make this easier.
@RaymondDay I'm not sure what casaos is. So perhaps it can't run the whisper addon.