šŸŽ¤ GLaSSIST - Desktop Voice Assistant for Home Assistant (Windows)

Share your Projects!
21

I can confirm the microphone selection is working. Thanks!

Is there a way to quickly mute the app, like during a meeting?

22

Took a little longer but here we are :wink:

image

Now you can stop catching wake word sound from tray menu

https://github.com/SmolinskiP/GLaSSIST/releases/download/1.1.2/GLaSSIST-Setup.exe

1 Like
23

It would be great if this could be toggled directly in Home Assistant using an entity.

24

Thank you so much for this little thing which does a a lot

it works ok on my main pc but on my old rusty Microsoft surface 3 windows tablet which I installed home assistant server using virtualbox, I get " assistant did not respond" error
how much horsepower does it need?
is there anyway you could optimize it for older windows machines please? like maybe add an option to remove that nice circle thingy or anything to reduce the cpu usage

1 Like
25

Hm, it takes less than 200mb RAM and 0.5% CPU time on my machine

i7-8700K / 16GB

I think the problem is somewhere else. What OS this surface? W10/W11 or older?

https://github.com/SmolinskiP/GLaSSIST/releases/download/1.1.2_debug/GLaSSIST-Setup.exe

Can you install this version and share command line output?

26

I see what you doing here, ā€œScarlet, kill yourselfā€;p

Iā€™m afraid this functionality requires adding a whole set of things that was totally not intended in project -possible, of course, and that functionality sounds nice.

I will think about it in weekend :wink:

27

itā€™s windows 11
I should mention this version is even slower to run

PyInstaller\loader\pyimod02_importers.py:450: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
=== GLaSSIST DESKTOP ===
Starting application...
Pre-initializing audio system...
Audio system ready
USING .ENV FILE: C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\.env
.ENV FILE CONTENTS:
# GLaSSIST Desktop Settings
# Generated automatically by the application

# === CONNECTION ===
HA_HOST=192.168.31.58:8123
HA_TOKEN=***HIDDEN*** (length: 183 chars)
HA_PIPELINE_ID=01jwxm9q3b75syrws84ycvwvxz

# === ACTIVATION ===
HA_HOTKEY=ctrl+shift+g

# === AUDIO ===
HA_SAMPLE_RATE=16000
HA_CHANNELS=1
HA_FRAME_DURATION_MS=30
HA_PADDING_MS=300
HA_MICROPHONE_INDEX=-1

# === VOICE DETECTION (VAD) ===
HA_VAD_MODE=3
HA_SILENCE_THRESHOLD_SEC=1.5

# === NETWORK ===
ANIMATION_PORT=8765

# === AUDIO FEEDBACK ===
HA_SOUND_FEEDBACK=true

# === WAKE WORD DETECTION ===
HA_WAKE_WORD_ENABLED=true
HA_WAKE_WORD_MODELS=glados,computer_v2
HA_WAKE_WORD_THRESHOLD=0.5
HA_WAKE_WORD_VAD_THRESHOLD=0.3
HA_WAKE_WORD_NOISE_SUPPRESSION=false

# === DEBUG ===
DEBUG=false

--------------------------------------------------
CHECKING CONFIGURATION...
 Configuration looks correct
--------------------------------------------------
 KEY SETTINGS:
   HA_HOST = 192.168.31.58:8123
   HA_PIPELINE_ID = 01jwxm9q3b75syrws84ycvwvxz
   HA_HOTKEY = ctrl+shift+g
   HA_VAD_MODE = 3
   HA_SOUND_FEEDBACK = true
   HA_WAKE_WORD_ENABLED = true
   DEBUG = false
   HA_WAKE_WORD_MODELS = glados,computer_v2
   HA_WAKE_WORD_THRESHOLD = 0.5
   HA_TOKEN = ***HIDDEN*** (183 chars)
==================================================
DEBUG: Trying to import openwakeword...
DEBUG: openwakeword imported successfully
DEBUG: Trying to import Model...
DEBUG: Model imported successfully
2025-06-09 11:16:29,972 - haassist - INFO - Initializing openWakeWord...
2025-06-09 11:16:29,982 - haassist - INFO - Found local model: C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\models\glados.onnx
2025-06-09 11:16:29,985 - haassist - INFO - Found local model: C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\models\computer_v2.onnx
2025-06-09 11:16:29,986 - haassist - INFO - Loading ONNX models on Windows: glados, computer_v2
DEBUG: About to create Model with kwargs: {'vad_threshold': 0.3, 'wakeword_models': ['C:\\Users\\mahzi\\AppData\\Local\\GLaSSIST\\_internal\\models\\glados.onnx', 'C:\\Users\\mahzi\\AppData\\Local\\GLaSSIST\\_internal\\models\\computer_v2.onnx']}
2025-06-09 11:16:30,000 - root - WARNING - Tried to import the tflite runtime, but it was not found. Trying to switching to onnxruntime instead, if appropriate models are available.
DEBUG: Model created successfully
2025-06-09 11:16:32,441 - haassist - INFO -  Wake word detection initialized
2025-06-09 11:16:32,446 - haassist - INFO -    Models: glados, computer_v2
2025-06-09 11:16:32,484 - haassist - INFO -    Threshold: 0.5
2025-06-09 11:16:32,488 - haassist - INFO -    VAD threshold: 0.3
2025-06-09 11:16:32,512 - haassist - INFO -    Noise suppression: False
2025-06-09 11:16:32,534 - haassist - INFO - Wake word detector initialized and enabled
2025-06-09 11:16:32,545 - haassist - INFO - Starting GLaSSIST Desktop...
2025-06-09 11:16:32,551 - asyncio - DEBUG - Using proactor: IocpProactor
2025-06-09 11:16:32,552 - haassist - INFO - Animation server starting on port 8765
2025-06-09 11:16:32,559 - haassist - INFO - Animation server started
2025-06-09 11:16:32,610 - haassist - INFO - Webview window configured (400x400, hidden from taskbar)
2025-06-09 11:16:33,062 - websockets.server - INFO - server listening on 127.0.0.1:8765
2025-06-09 11:16:33,066 - websockets.server - INFO - server listening on [::1]:8765
2025-06-09 11:16:33,067 - haassist - INFO - Animation server running at ws://localhost:8765
2025-06-09 11:16:34,485 - haassist - INFO - Keyboard shortcut set: ctrl+shift+g
2025-06-09 11:16:34,560 - PIL.Image - DEBUG - Importing AvifImagePlugin
2025-06-09 11:16:34,564 - PIL.Image - DEBUG - Importing BlpImagePlugin
2025-06-09 11:16:34,574 - PIL.Image - DEBUG - Importing BmpImagePlugin
2025-06-09 11:16:34,575 - PIL.Image - DEBUG - Importing BufrStubImagePlugin
2025-06-09 11:16:34,578 - PIL.Image - DEBUG - Importing CurImagePlugin
2025-06-09 11:16:34,582 - PIL.Image - DEBUG - Importing DcxImagePlugin
2025-06-09 11:16:34,588 - PIL.Image - DEBUG - Importing DdsImagePlugin
2025-06-09 11:16:34,624 - PIL.Image - DEBUG - Importing EpsImagePlugin
2025-06-09 11:16:34,637 - PIL.Image - DEBUG - Importing FitsImagePlugin
2025-06-09 11:16:34,649 - PIL.Image - DEBUG - Importing FliImagePlugin
2025-06-09 11:16:34,652 - PIL.Image - DEBUG - Importing FpxImagePlugin
2025-06-09 11:16:34,656 - PIL.Image - DEBUG - Image: failed to import FpxImagePlugin: No module named 'olefile'
2025-06-09 11:16:34,663 - PIL.Image - DEBUG - Importing FtexImagePlugin
2025-06-09 11:16:34,669 - PIL.Image - DEBUG - Importing GbrImagePlugin
2025-06-09 11:16:34,723 - PIL.Image - DEBUG - Importing GifImagePlugin
2025-06-09 11:16:34,726 - PIL.Image - DEBUG - Importing GribStubImagePlugin
2025-06-09 11:16:34,729 - PIL.Image - DEBUG - Importing Hdf5StubImagePlugin
2025-06-09 11:16:34,732 - PIL.Image - DEBUG - Importing IcnsImagePlugin
2025-06-09 11:16:34,751 - PIL.Image - DEBUG - Importing IcoImagePlugin
2025-06-09 11:16:34,762 - PIL.Image - DEBUG - Importing ImImagePlugin
2025-06-09 11:16:34,873 - PIL.Image - DEBUG - Importing ImtImagePlugin
2025-06-09 11:16:34,989 - PIL.Image - DEBUG - Importing IptcImagePlugin
2025-06-09 11:16:35,005 - PIL.Image - DEBUG - Importing JpegImagePlugin
2025-06-09 11:16:35,007 - PIL.Image - DEBUG - Importing Jpeg2KImagePlugin
2025-06-09 11:16:35,008 - PIL.Image - DEBUG - Importing McIdasImagePlugin
2025-06-09 11:16:35,013 - PIL.Image - DEBUG - Importing MicImagePlugin
2025-06-09 11:16:35,039 - PIL.Image - DEBUG - Image: failed to import MicImagePlugin: No module named 'olefile'
2025-06-09 11:16:35,047 - PIL.Image - DEBUG - Importing MpegImagePlugin
2025-06-09 11:16:35,052 - PIL.Image - DEBUG - Importing MpoImagePlugin
2025-06-09 11:16:35,120 - PIL.Image - DEBUG - Importing MspImagePlugin
2025-06-09 11:16:35,138 - PIL.Image - DEBUG - Importing PalmImagePlugin
2025-06-09 11:16:35,151 - PIL.Image - DEBUG - Importing PcdImagePlugin
2025-06-09 11:16:35,153 - PIL.Image - DEBUG - Importing PcxImagePlugin
2025-06-09 11:16:35,163 - PIL.Image - DEBUG - Importing PdfImagePlugin
2025-06-09 11:16:35,214 - PIL.Image - DEBUG - Importing PixarImagePlugin
2025-06-09 11:16:35,241 - PIL.Image - DEBUG - Importing PngImagePlugin
2025-06-09 11:16:35,241 - PIL.Image - DEBUG - Importing PpmImagePlugin
2025-06-09 11:16:35,242 - PIL.Image - DEBUG - Importing PsdImagePlugin
2025-06-09 11:16:35,245 - PIL.Image - DEBUG - Importing QoiImagePlugin
2025-06-09 11:16:35,251 - PIL.Image - DEBUG - Importing SgiImagePlugin
2025-06-09 11:16:35,256 - PIL.Image - DEBUG - Importing SpiderImagePlugin
2025-06-09 11:16:35,261 - PIL.Image - DEBUG - Importing SunImagePlugin
2025-06-09 11:16:35,265 - PIL.Image - DEBUG - Importing TgaImagePlugin
2025-06-09 11:16:35,269 - PIL.Image - DEBUG - Importing TiffImagePlugin
2025-06-09 11:16:35,269 - PIL.Image - DEBUG - Importing WebPImagePlugin
2025-06-09 11:16:35,309 - PIL.Image - DEBUG - Importing WmfImagePlugin
2025-06-09 11:16:35,318 - PIL.Image - DEBUG - Importing XbmImagePlugin
2025-06-09 11:16:35,325 - PIL.Image - DEBUG - Importing XpmImagePlugin
2025-06-09 11:16:35,329 - PIL.Image - DEBUG - Importing XVThumbImagePlugin
2025-06-09 11:16:35,336 - PIL.PngImagePlugin - DEBUG - STREAM b'IHDR' 161894 13
2025-06-09 11:16:35,337 - PIL.PngImagePlugin - DEBUG - STREAM b'orNT' 161919 1
2025-06-09 11:16:35,337 - PIL.PngImagePlugin - DEBUG - b'orNT' 161919 1 (unknown)
2025-06-09 11:16:35,339 - PIL.PngImagePlugin - DEBUG - STREAM b'IDAT' 161932 32768
2025-06-09 11:16:35,360 - haassist - INFO - Loaded tray icon: C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\img\icon.ico
2025-06-09 11:16:35,369 - haassist - INFO - System tray icon created
2025-06-09 11:16:35,372 - haassist - INFO - System tray started
2025-06-09 11:16:35,594 - haassist - INFO - Wake word using default microphone: Microphone (Intel SST Audio Dev
2025-06-09 11:16:35,840 - haassist - INFO - Audio stream initialized for wake word detection
2025-06-09 11:16:36,003 - haassist - INFO -  Wake word detection started
2025-06-09 11:16:36,008 - haassist - DEBUG - Wake word detection thread priority lowered
2025-06-09 11:16:36,014 - haassist - INFO -  Wake word detection started
2025-06-09 11:16:36,017 - haassist - INFO - Wake word detection loop started
2025-06-09 11:16:36,043 - haassist - INFO - Starting interface...
2025-06-09 11:16:38,263 - haassist - INFO - Attempting to hide window from taskbar...
2025-06-09 11:16:38,284 - haassist - WARNING - Failed to hide window from taskbar
2025-06-09 11:17:17,038 - websockets.server - DEBUG - = connection is CONNECTING
2025-06-09 11:17:18,146 - websockets.server - DEBUG - < GET / HTTP/1.1
2025-06-09 11:17:18,422 - websockets.server - DEBUG - < Host: localhost:8765
2025-06-09 11:17:18,571 - websockets.server - DEBUG - < Connection: Upgrade
2025-06-09 11:17:18,588 - websockets.server - DEBUG - < Pragma: no-cache
2025-06-09 11:17:18,603 - websockets.server - DEBUG - < Cache-Control: no-cache
2025-06-09 11:17:18,630 - websockets.server - DEBUG - < User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36 Edg/137.0.0.0
2025-06-09 11:17:18,655 - websockets.server - DEBUG - < Upgrade: websocket
2025-06-09 11:17:18,666 - websockets.server - DEBUG - < Origin: http://127.0.0.1:4462
2025-06-09 11:17:18,667 - websockets.server - DEBUG - < Sec-WebSocket-Version: 13
2025-06-09 11:17:18,676 - websockets.server - DEBUG - < Accept-Encoding: gzip, deflate, br, zstd
2025-06-09 11:17:18,680 - websockets.server - DEBUG - < Accept-Language: en-US,en;q=0.9
2025-06-09 11:17:18,682 - websockets.server - DEBUG - < Sec-WebSocket-Key: tGHmFbUznT3Vihl+ycV6bg==
2025-06-09 11:17:18,685 - websockets.server - DEBUG - < Sec-WebSocket-Extensions: permessage-deflate; client_max_window_bits
2025-06-09 11:17:18,745 - websockets.server - DEBUG - > HTTP/1.1 101 Switching Protocols
2025-06-09 11:17:19,024 - websockets.server - DEBUG - > Date: Mon, 09 Jun 2025 07:47:18 GMT
2025-06-09 11:17:19,179 - websockets.server - DEBUG - > Upgrade: websocket
2025-06-09 11:17:19,245 - websockets.server - DEBUG - > Connection: Upgrade
2025-06-09 11:17:19,368 - websockets.server - DEBUG - > Sec-WebSocket-Accept: 5+GDLeL4idXnMAP0Dbg63tfFiGE=
2025-06-09 11:17:19,448 - websockets.server - DEBUG - > Sec-WebSocket-Extensions: permessage-deflate; server_max_window_bits=12; client_max_window_bits=12
2025-06-09 11:17:19,493 - websockets.server - DEBUG - > Server: Python/3.13 websockets/15.0.1
2025-06-09 11:17:19,543 - websockets.server - DEBUG - = connection is OPEN
2025-06-09 11:17:19,558 - websockets.server - INFO - connection open
2025-06-09 11:17:19,576 - haassist - INFO - New animation client connected: ('::1', 51754, 0, 0)
2025-06-09 11:17:19,607 - websockets.server - DEBUG - > TEXT '{"type": "state_change", "state": "hidden"}' [43 bytes]
2025-06-09 11:17:23,450 - websockets.server - DEBUG - < TEXT '{"type":"ready"}' [16 bytes]
2025-06-09 11:17:23,466 - haassist - INFO - Animation client ready
2025-06-09 11:17:46,731 - websockets.server - DEBUG - < TEXT '{"type":"ping"}' [15 bytes]
2025-06-09 11:17:46,754 - websockets.server - DEBUG - > TEXT '{"type": "pong"}' [16 bytes]
2025-06-09 11:17:54,685 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.998)
2025-06-09 11:17:54,693 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.998)
2025-06-09 11:17:54,717 - asyncio - DEBUG - Using proactor: IocpProactor
2025-06-09 11:17:54,947 - haassist - INFO - Animation state change: hidden -> listening
2025-06-09 11:17:54,984 - websockets.server - DEBUG - > TEXT '{"type": "state_change", "state": "listening", ...estamp": 1749455274961}' [74 bytes]
2025-06-09 11:17:55,096 - haassist - DEBUG - Playing sound: activation
2025-06-09 11:17:55,307 - haassist - INFO - VAD initialized: mode=3, silence threshold=1.5s, chunk size=480
2025-06-09 11:17:55,313 - haassist - INFO - AudioManager initialized: 16000Hz, 1 channel(s), chunk 480
2025-06-09 11:17:55,727 - haassist - INFO - Checking pipeline availability: 01jwxm9q3b75syrws84ycvwvxz
2025-06-09 11:17:57,070 - haassist - DEBUG - Audio device 0: Microsoft Sound Mapper - Input - input channels: 2
2025-06-09 11:17:57,071 - haassist - INFO - Found microphone: Microsoft Sound Mapper - Input
2025-06-09 11:17:57,076 - haassist - DEBUG - Audio device 1: Microphone (Intel SST Audio Dev - input channels: 2
2025-06-09 11:17:57,089 - haassist - INFO - Found default microphone: Microphone (Intel SST Audio Dev
2025-06-09 11:17:57,092 - haassist - DEBUG - Audio device 2: Microsoft Sound Mapper - Output - input channels: 0
2025-06-09 11:17:57,098 - haassist - DEBUG - Audio device 3: Speakers/Headphones (Intel SST  - input channels: 0
2025-06-09 11:17:57,101 - haassist - DEBUG - Audio device 4: Primary Sound Capture Driver - input channels: 2
2025-06-09 11:17:57,102 - haassist - DEBUG - Audio device 5: Microphone (Intel SST Audio Device (WDM)) - input channels: 2
2025-06-09 11:17:57,104 - haassist - DEBUG - Audio device 6: Primary Sound Driver - input channels: 0
2025-06-09 11:17:57,105 - haassist - DEBUG - Audio device 7: Speakers/Headphones (Intel SST Audio Device (WDM)) - input channels: 0
2025-06-09 11:17:57,107 - haassist - DEBUG - Audio device 8: Speakers/Headphones (Intel SST Audio Device (WDM)) - input channels: 0
2025-06-09 11:17:57,108 - haassist - DEBUG - Audio device 9: Microphone (Intel SST Audio Device (WDM)) - input channels: 2
2025-06-09 11:17:57,111 - haassist - DEBUG - Audio device 10: Speakers (IntelSST Audio Wave for IHF) - input channels: 0
2025-06-09 11:17:57,116 - haassist - DEBUG - Audio device 11: Microphone (IntelSST Audio Wave for DMIC) - input channels: 2
2025-06-09 11:17:58,107 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.998)
2025-06-09 11:17:58,131 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.998)
2025-06-09 11:17:58,134 - haassist - INFO - Application is busy, ignoring wake word
2025-06-09 11:17:58,677 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.999)
2025-06-09 11:17:58,678 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.999)
2025-06-09 11:17:58,678 - haassist - INFO - Application is busy, ignoring wake word
2025-06-09 11:17:59,434 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.999)
2025-06-09 11:17:59,436 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.999)
2025-06-09 11:17:59,436 - haassist - INFO - Application is busy, ignoring wake word
2025-06-09 11:18:00,071 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.999)
2025-06-09 11:18:00,074 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.999)
2025-06-09 11:18:00,076 - haassist - INFO - Application is busy, ignoring wake word
2025-06-09 11:18:00,110 - haassist - INFO - Audio stream initialized: 16000 Hz, 1 channel(s), chunk 480
2025-06-09 11:18:00,255 - haassist - INFO - Connecting to Home Assistant: ws://192.168.31.58:8123/api/websocket
2025-06-09 11:18:01,709 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.998)
2025-06-09 11:18:01,710 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.998)
2025-06-09 11:18:01,710 - haassist - INFO - Application is busy, ignoring wake word
2025-06-09 11:18:02,926 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.997)
2025-06-09 11:18:02,927 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.997)
2025-06-09 11:18:02,966 - websockets.client - DEBUG - = connection is CONNECTING
2025-06-09 11:18:03,243 - websockets.client - DEBUG - > GET /api/websocket HTTP/1.1
2025-06-09 11:18:03,245 - websockets.client - DEBUG - > Host: 192.168.31.58:8123
2025-06-09 11:18:03,247 - websockets.client - DEBUG - > Upgrade: websocket
2025-06-09 11:18:03,248 - websockets.client - DEBUG - > Connection: Upgrade
2025-06-09 11:18:03,250 - websockets.client - DEBUG - > Sec-WebSocket-Key: I6dVnXihUbAF1OfJXJRTxA==
2025-06-09 11:18:03,251 - websockets.client - DEBUG - > Sec-WebSocket-Version: 13
2025-06-09 11:18:03,061 - haassist - INFO - Application is busy, ignoring wake word
2025-06-09 11:18:03,253 - websockets.client - DEBUG - > Sec-WebSocket-Extensions: permessage-deflate; client_max_window_bits
2025-06-09 11:18:03,456 - websockets.client - DEBUG - > User-Agent: Python/3.13 websockets/15.0.1
2025-06-09 11:18:03,615 - websockets.client - DEBUG - < HTTP/1.1 101 Switching Protocols
2025-06-09 11:18:03,616 - websockets.client - DEBUG - < Upgrade: websocket
2025-06-09 11:18:03,620 - websockets.client - DEBUG - < Connection: upgrade
2025-06-09 11:18:03,621 - websockets.client - DEBUG - < Sec-WebSocket-Accept: XjHJa0eersH2TJ7xtERFWOo5U2k=
2025-06-09 11:18:03,622 - websockets.client - DEBUG - < Sec-WebSocket-Extensions: permessage-deflate
2025-06-09 11:18:03,622 - websockets.client - DEBUG - < Date: Mon, 09 Jun 2025 07:48:03 GMT
2025-06-09 11:18:03,624 - websockets.client - DEBUG - < Server: Python/3.13 aiohttp/3.11.18
2025-06-09 11:18:03,855 - websockets.client - DEBUG - = connection is OPEN
2025-06-09 11:18:03,859 - haassist - INFO - Connection established
2025-06-09 11:18:03,905 - websockets.client - DEBUG - < TEXT '{"type":"auth_required","ha_version":"2025.5.3"}' [48 bytes]
2025-06-09 11:18:03,907 - websockets.client - DEBUG - > TEXT '{"type": "auth", "access_token": "eyJhbGciOiJIU...KGYCz6a7p4R6vdyjaD5JE"}' [219 bytes]
2025-06-09 11:18:04,190 - websockets.client - DEBUG - < TEXT '{"type":"auth_ok","ha_version":"2025.5.3"}' [42 bytes]
2025-06-09 11:18:04,192 - haassist - INFO - Authentication completed successfully
2025-06-09 11:18:04,215 - haassist - INFO - šŸ” Fetching Assist pipelines...
2025-06-09 11:18:04,247 - websockets.client - DEBUG - > TEXT '{"id": 1, "type": "assist_pipeline/pipeline/list"}' [50 bytes]
2025-06-09 11:18:04,835 - websockets.client - DEBUG - < TEXT '{"id":1,"type":"result","success":true,"result"...9q3b75syrws84ycvwvxz"}}' [834 bytes]
2025-06-09 11:18:04,837 - haassist - INFO - āœ… Found 2 pipelines
2025-06-09 11:18:04,837 - haassist - INFO - šŸ† Preferred pipeline: 01jwxm9q3b75syrws84ycvwvxz
2025-06-09 11:18:04,839 - haassist - INFO -   šŸ“‹ Home Assistant
2025-06-09 11:18:04,841 - haassist - INFO -       ID: 01jwxhv3mv8h2zg2vvpteftva8
2025-06-09 11:18:04,842 - haassist - INFO -       Language: en
2025-06-09 11:18:04,843 - haassist - INFO -       Conversation: conversation.home_assistant
2025-06-09 11:18:04,846 - haassist - INFO -       STT: None
2025-06-09 11:18:04,847 - haassist - INFO -       TTS: None (None)
2025-06-09 11:18:04,936 - haassist - INFO -   šŸ“‹ Local sst and tts ā­ (PREFERRED)
2025-06-09 11:18:04,999 - haassist - INFO -       ID: 01jwxm9q3b75syrws84ycvwvxz
2025-06-09 11:18:05,199 - haassist - INFO -       Language: en
2025-06-09 11:18:05,207 - haassist - INFO -       Conversation: conversation.home_assistant
2025-06-09 11:18:05,210 - haassist - INFO -       STT: stt.speech_to_phrase
2025-06-09 11:18:05,213 - haassist - INFO -       TTS: tts.piper (en_US-amy-low)
2025-06-09 11:18:05,216 - haassist - INFO - šŸ LOADED 2 PIPELINES
2025-06-09 11:18:05,218 - haassist - INFO - Connected to Home Assistant
2025-06-09 11:18:05,222 - haassist - INFO - Starting Assist pipeline
2025-06-09 11:18:05,224 - haassist - INFO - Using pipeline ID: 01jwxm9q3b75syrws84ycvwvxz
2025-06-09 11:18:05,226 - websockets.client - DEBUG - > TEXT '{"id": 2, "type": "assist_pipeline/run", "start...m9q3b75syrws84ycvwvxz"}' [172 bytes]
2025-06-09 11:18:05,684 - websockets.client - DEBUG - < TEXT '{"id":2,"type":"result","success":true,"result":null}' [53 bytes]
2025-06-09 11:18:05,686 - haassist - INFO - Received: {'id': 2, 'type': 'result', 'success': True, 'result': None}
2025-06-09 11:18:05,696 - websockets.client - DEBUG - < TEXT '{"id":2,"type":"event","event":{"type":"run-sta...7:48:05.638111+00:00"}}' [393 bytes]
2025-06-09 11:18:05,697 - haassist - INFO - Received: {'id': 2, 'type': 'event', 'event': {'type': 'run-start', 'data': {'pipeline': '01jwxm9q3b75syrws84ycvwvxz', 'language': 'en', 'conversation_id': '01JX9TJBAJX73FWBBX4WXN1SX3', 'runner_data': {'stt_binary_handler_id': 1, 'timeout': 30}, 'tts_output': {'token': 'ckiECo2yRPUYKyj4-kEZhg.mp3', 'url': '/api/tts_proxy/ckiECo2yRPUYKyj4-kEZhg.mp3', 'mime_type': 'audio/mpeg'}}, 'timestamp': '2025-06-09T07:48:05.638111+00:00'}}
2025-06-09 11:18:05,702 - haassist - INFO - Received stt_binary_handler_id: 1
2025-06-09 11:18:05,704 - haassist - INFO - Saved audio URL from run-start: /api/tts_proxy/ckiECo2yRPUYKyj4-kEZhg.mp3
2025-06-09 11:18:05,706 - haassist - INFO - Assist pipeline started successfully

=== LISTENING ===
(Waiting for voice, speak to microphone...)
2025-06-09 11:18:05,717 - haassist - INFO - Starting recording with VAD detection
2025-06-09 11:18:16,789 - websockets.server - DEBUG - < TEXT '{"type":"ping"}' [15 bytes]
2025-06-09 11:18:16,933 - haassist - INFO - Speech start detected
2025-06-09 11:18:16,942 - websockets.server - DEBUG - > TEXT '{"type": "pong"}' [16 bytes]
2025-06-09 11:18:17,002 - haassist - INFO - Started speech processing
2025-06-09 11:18:17,372 - websockets.client - DEBUG - > BINARY 01 ea 01 e9 01 c5 01 6a 01 b7 01 b9 01 89 01 7c ... 66 fd 40 fd a0 fd ed fd [961 bytes]
2025-06-09 11:18:17,423 - websockets.client - DEBUG - > BINARY 01 32 fe d7 fe 5a ff ca ff ef ff 1d 00 33 00 50 ... 60 01 65 01 93 01 51 01 [961 bytes]
2025-06-09 11:18:17,699 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [0.48450306685366...estamp": 1749455297371}' [730 bytes]
2025-06-09 11:18:17,841 - websockets.client - DEBUG - > BINARY 01 10 01 5d 01 ad 01 41 02 9d 02 31 02 e3 01 49 ... a7 fe 77 fe 3b fe 40 fe [961 bytes]
2025-06-09 11:18:17,846 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [0.59947123575012...estamp": 1749455297422}' [724 bytes]
2025-06-09 11:18:17,856 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [0.85879683912565...estamp": 1749455297841}' [723 bytes]
2025-06-09 11:18:17,931 - websockets.client - DEBUG - > BINARY 01 69 fe 1c fe d9 fd 1e fe d4 fe 1e 00 74 01 cb ... 57 ff 39 ff 1f ff f4 fe [961 bytes]
2025-06-09 11:18:17,933 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [0.91159848894787...estamp": 1749455297930}' [729 bytes]
2025-06-09 11:18:17,940 - websockets.client - DEBUG - > BINARY 01 d8 fe 70 fe 10 fe b4 fd 41 fd 35 fd 62 fd 79 ... 79 03 51 03 d1 02 58 02 [961 bytes]
2025-06-09 11:18:17,941 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [0.90293031907533...estamp": 1749455297939}' [721 bytes]
2025-06-09 11:18:17,960 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.167055848...estamp": 1749455297958}' [733 bytes]
2025-06-09 11:18:17,963 - websockets.client - DEBUG - > BINARY 01 9d 01 86 01 a2 01 b3 01 b0 01 da 01 da 01 bd ... 45 00 60 00 5d 00 16 00 [961 bytes]
2025-06-09 11:18:18,249 - websockets.client - DEBUG - > BINARY 01 4e 00 48 00 54 00 cb 00 2b 01 53 01 4f 01 34 ... ab fe 61 fe 13 fe ba fd [961 bytes]
2025-06-09 11:18:18,251 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.488944997...estamp": 1749455298248}' [733 bytes]
2025-06-09 11:18:18,469 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.258328764...estamp": 1749455298468}' [735 bytes]
2025-06-09 11:18:18,471 - websockets.client - DEBUG - > BINARY 01 8b fe 5d fe 18 fe 07 fe 13 fe fd fd f5 fd fe ... 54 00 62 00 6c 00 83 00 [961 bytes]
2025-06-09 11:18:18,496 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.445842408...estamp": 1749455298491}' [728 bytes]
2025-06-09 11:18:18,502 - websockets.client - DEBUG - > BINARY 01 c2 00 21 01 32 01 23 01 75 01 c3 01 cd 01 d6 ... 35 fe e6 fd 84 fd 1f fd [961 bytes]
2025-06-09 11:18:18,756 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.481414828...estamp": 1749455298755}' [725 bytes]
2025-06-09 11:18:18,758 - websockets.client - DEBUG - > BINARY 01 5d fd 40 fd e2 fc 40 fd 44 fd e7 fc b1 fc 75 ... 45 00 94 00 d3 00 11 01 [961 bytes]
2025-06-09 11:18:18,847 - websockets.client - DEBUG - > BINARY 01 17 00 f2 ff f6 ff dd ff ea ff 0c 00 ed ff 04 ... d9 ff 05 00 45 00 c9 ff [961 bytes]
2025-06-09 11:18:18,951 - websockets.client - DEBUG - > BINARY 01 d5 00 d7 00 dc 00 cd 00 e1 00 e4 00 e3 00 de ... ec ff 06 00 ff ff f8 ff [961 bytes]
2025-06-09 11:18:18,848 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.215752234...estamp": 1749455298844}' [717 bytes]
2025-06-09 11:18:18,965 - websockets.client - DEBUG - > BINARY 01 34 00 2c 00 33 00 2f 00 29 00 23 00 15 00 0d ... 8f 00 81 00 78 00 66 00 [961 bytes]
2025-06-09 11:18:19,214 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.160380413...estamp": 1749455298950}' [727 bytes]
2025-06-09 11:18:19,701 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.122880835...estamp": 1749455298963}' [728 bytes]
2025-06-09 11:18:19,705 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.104435893...estamp": 1749455299251}' [725 bytes]
2025-06-09 11:18:19,252 - websockets.client - DEBUG - > BINARY 01 79 00 5d 00 53 00 5e 00 62 00 66 00 79 00 67 ... 2e 00 36 00 18 00 2b 00 [961 bytes]
2025-06-09 11:18:19,789 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.096506487...estamp": 1749455299788}' [721 bytes]
2025-06-09 11:18:19,805 - websockets.client - DEBUG - > BINARY 01 ee ff e5 ff e5 ff e8 ff cf ff d4 ff d7 ff c2 ... 58 00 57 00 6d 00 42 00 [961 bytes]
2025-06-09 11:18:20,103 - websockets.client - DEBUG - > BINARY 01 29 00 2e 00 2f 00 22 00 1f 00 1a 00 10 00 08 ... 22 00 0e 00 fa ff f7 ff [961 bytes]
2025-06-09 11:18:20,113 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.173508228...estamp": 1749455300102}' [721 bytes]
2025-06-09 11:18:20,592 - haassist - INFO - Speech end detected after 1.64s silence
2025-06-09 11:18:20,613 - websockets.client - DEBUG - > BINARY 01 f2 ff 04 00 f8 ff 0c 00 17 00 25 00 16 00 24 ... 35 ff 20 ff 25 ff 46 ff [961 bytes]
2025-06-09 11:18:20,618 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.222955011...estamp": 1749455300612}' [718 bytes]
2025-06-09 11:18:21,224 - haassist - INFO - Recording completed after 15.5s, processed 335 chunks
2025-06-09 11:18:21,234 - haassist - INFO - === SWITCHING TO PROCESSING ===
2025-06-09 11:18:21,572 - haassist - INFO - Animation state change: listening -> processing
2025-06-09 11:18:21,581 - websockets.client - DEBUG - < TEXT '{"id":2,"type":"event","event":{"type":"stt-sta...7:48:05.640528+00:00"}}' [244 bytes]
2025-06-09 11:18:21,583 - websockets.server - DEBUG - > TEXT '{"type": "state_change", "state": "processing",...estamp": 1749455301574}' [75 bytes]
2025-06-09 11:18:22,382 - haassist - INFO - Sending end of audio signal
2025-06-09 11:18:22,382 - websockets.client - DEBUG - > BINARY 01 [1 byte]
2025-06-09 11:18:22,385 - haassist - INFO - Recording completed
2025-06-09 11:18:22,386 - haassist - INFO - Audio sent successfully
2025-06-09 11:18:22,387 - haassist - INFO - === RECEIVING RESPONSE ===
2025-06-09 11:18:22,390 - haassist - INFO - Received: {'id': 2, 'type': 'event', 'event': {'type': 'stt-start', 'data': {'engine': 'stt.speech_to_phrase', 'metadata': {'language': 'en', 'format': 'wav', 'codec': 'pcm', 'bit_rate': 16, 'sample_rate': 16000, 'channel': 1}}, 'timestamp': '2025-06-09T07:48:05.640528+00:00'}}
2025-06-09 11:18:23,869 - websockets.client - DEBUG - > PING be 7c ed db [binary, 4 bytes]
2025-06-09 11:18:23,872 - websockets.client - DEBUG - % sent keepalive ping
2025-06-09 11:18:23,880 - websockets.client - DEBUG - < PONG be 7c ed db [binary, 4 bytes]
2025-06-09 11:18:23,881 - websockets.client - DEBUG - % received keepalive pong
2025-06-09 11:18:27,397 - haassist - WARNING - Timeout during single message reception

No response from assistant or processing error.
2025-06-09 11:18:27,401 - haassist - INFO - Animation state change: processing -> error
2025-06-09 11:18:27,402 - haassist - INFO - Error message: Assistant did not respond
2025-06-09 11:18:27,405 - websockets.server - DEBUG - > TEXT '{"type": "state_change", "state": "error", "tim...stant did not respond"}' [115 bytes]
2025-06-09 11:18:32,888 - haassist - INFO - Animation state change: error -> hidden
2025-06-09 11:18:32,893 - websockets.server - DEBUG - > TEXT '{"type": "state_change", "state": "hidden", "timestamp": 1749455312889}' [71 bytes]
2025-06-09 11:18:33,546 - haassist - DEBUG - Playing sound: deactivation
2025-06-09 11:18:33,547 - haassist - INFO - Cleaning up voice command session...
2025-06-09 11:18:33,572 - haassist - INFO - Audio stream closed
2025-06-09 11:18:33,577 - haassist - INFO - PyAudio terminated
2025-06-09 11:18:33,578 - haassist - DEBUG - Temp audio manager closed
2025-06-09 11:18:33,746 - websockets.client - DEBUG - > CLOSE 1000 (OK) [2 bytes]
2025-06-09 11:18:33,822 - websockets.client - DEBUG - = connection is CLOSING
2025-06-09 11:18:33,974 - websockets.client - DEBUG - < CLOSE 1000 (OK) [2 bytes]
2025-06-09 11:18:33,995 - websockets.client - DEBUG - < EOF
2025-06-09 11:18:33,996 - websockets.client - DEBUG - > EOF
2025-06-09 11:18:34,082 - websockets.client - DEBUG - = connection is CLOSED
2025-06-09 11:18:34,268 - websockets.client - DEBUG - x half-closing TCP connection
2025-06-09 11:18:34,470 - haassist - INFO - Connection closed
2025-06-09 11:18:34,470 - haassist - DEBUG - Temp HA client closed
2025-06-09 11:18:34,471 - haassist - INFO - Voice command session cleanup completed
2025-06-09 11:18:46,701 - websockets.se
1 Like
28

What speech-to-text engine are you using? Cloud or local? If local, can you check that STT is working on your tablet at all? And how long i take to generate response?

Application may be slow and i can and i will make button to turn off the animation because thatā€™s good idea - no problem amigo :wink: but i donā€™t think itā€™s because of heavy application, it seems like problem with generating speech to text on HA side - if you are using local model, it can be because of timeout.

Iā€™m waiting for your response and then goin to work :wink: IMO itā€™s problem with local model taking too long time for response to generate, and application not waiting enough. Propably just increasing waiting for a message from HA will do the trick.

edit: and yes, debug version can be slower than main

29

itā€™s local
I still havenā€™t been able to make assist directly work on the tablet. thatā€™s why I installed glassist
but on my android phone it works fine

ha3
ha3606Ɨ893 42.9 KB

30

https://github.com/SmolinskiP/GLaSSIST/releases/download/1.1.2/GLaSSIST-Debug.exe

I increased timeouts from 5 to 15 seconds - letā€™s see if this helps.

What you mean by saying that you was not able to make assist work on the tablet? Maybe the problem is deeper? GLaSSIST is using existing infrastructure, it just connects to data, itā€™s not doing any STT TTS magic on itā€™s own so if assist isnā€™t working it can be it.

If you wish we can make some AeroAdmin remote session, i can check your setup and look whatā€™s going on there.

31

assistant did not respond

PyInstaller\loader\pyimod02_importers.py:450: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
=== GLaSSIST DESKTOP ===
Starting application...
Pre-initializing audio system...
Audio system ready
USING .ENV FILE: C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\.env
.ENV FILE CONTENTS:
# GLaSSIST Desktop Settings
# Generated automatically by the application

# === CONNECTION ===
HA_HOST=192.168.31.58:8123
HA_TOKEN=***HIDDEN*** (length: 183 chars)
HA_PIPELINE_ID=01jwxm9q3b75syrws84ycvwvxz

# === ACTIVATION ===
HA_HOTKEY=ctrl+shift+g

# === AUDIO ===
HA_SAMPLE_RATE=16000
HA_CHANNELS=1
HA_FRAME_DURATION_MS=30
HA_PADDING_MS=300
HA_MICROPHONE_INDEX=-1

# === VOICE DETECTION (VAD) ===
HA_VAD_MODE=3
HA_SILENCE_THRESHOLD_SEC=1.5

# === NETWORK ===
ANIMATION_PORT=8765

# === AUDIO FEEDBACK ===
HA_SOUND_FEEDBACK=false

# === WAKE WORD DETECTION ===
HA_WAKE_WORD_ENABLED=true
HA_WAKE_WORD_MODELS=glados,computer_v2
HA_WAKE_WORD_THRESHOLD=0.5
HA_WAKE_WORD_VAD_THRESHOLD=0.3
HA_WAKE_WORD_NOISE_SUPPRESSION=false

# === DEBUG ===
DEBUG=true

--------------------------------------------------
CHECKING CONFIGURATION...
 Configuration looks correct
--------------------------------------------------
 KEY SETTINGS:
   HA_HOST = 192.168.31.58:8123
   HA_PIPELINE_ID = 01jwxm9q3b75syrws84ycvwvxz
   HA_HOTKEY = ctrl+shift+g
   HA_VAD_MODE = 3
   HA_SOUND_FEEDBACK = false
   HA_WAKE_WORD_ENABLED = true
   DEBUG = true
   HA_WAKE_WORD_MODELS = glados,computer_v2
   HA_WAKE_WORD_THRESHOLD = 0.5
   HA_TOKEN = ***HIDDEN*** (183 chars)
==================================================
DEBUG: Trying to import openwakeword...
DEBUG: openwakeword imported successfully
DEBUG: Trying to import Model...
DEBUG: Model imported successfully
2025-06-09 15:30:36,865 - haassist - INFO - Initializing openWakeWord...
2025-06-09 15:30:36,870 - haassist - INFO - Found local model: C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\models\glados.onnx
2025-06-09 15:30:36,872 - haassist - INFO - Found local model: C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\models\computer_v2.onnx
2025-06-09 15:30:36,873 - haassist - INFO - Loading ONNX models on Windows: glados, computer_v2
DEBUG: About to create Model with kwargs: {'vad_threshold': 0.3, 'wakeword_models': ['C:\\Users\\mahzi\\AppData\\Local\\GLaSSIST\\_internal\\models\\glados.onnx', 'C:\\Users\\mahzi\\AppData\\Local\\GLaSSIST\\_internal\\models\\computer_v2.onnx']}
2025-06-09 15:30:36,877 - root - WARNING - Tried to import the tflite runtime, but it was not found. Trying to switching to onnxruntime instead, if appropriate models are available.
DEBUG: Model created successfully
2025-06-09 15:30:38,304 - haassist - INFO -  Wake word detection initialized
2025-06-09 15:30:38,304 - haassist - INFO -    Models: glados, computer_v2
2025-06-09 15:30:38,305 - haassist - INFO -    Threshold: 0.5
2025-06-09 15:30:38,306 - haassist - INFO -    VAD threshold: 0.3
2025-06-09 15:30:38,306 - haassist - INFO -    Noise suppression: False
2025-06-09 15:30:38,306 - haassist - INFO - Wake word detector initialized and enabled
2025-06-09 15:30:38,307 - haassist - INFO - Starting GLaSSIST Desktop...
2025-06-09 15:30:38,310 - haassist - INFO - Animation server starting on port 8765
2025-06-09 15:30:38,311 - haassist - INFO - Animation server started
2025-06-09 15:30:38,311 - asyncio - DEBUG - Using proactor: IocpProactor
2025-06-09 15:30:38,321 - haassist - INFO - Webview window configured (400x400, hidden from taskbar)
2025-06-09 15:30:38,534 - websockets.server - INFO - server listening on [::1]:8765
2025-06-09 15:30:38,536 - websockets.server - INFO - server listening on 127.0.0.1:8765
2025-06-09 15:30:38,538 - haassist - INFO - Animation server running at ws://localhost:8765
2025-06-09 15:30:39,404 - haassist - INFO - Keyboard shortcut set: ctrl+shift+g
2025-06-09 15:30:39,486 - PIL.Image - DEBUG - Importing AvifImagePlugin
2025-06-09 15:30:39,490 - PIL.Image - DEBUG - Importing BlpImagePlugin
2025-06-09 15:30:39,504 - PIL.Image - DEBUG - Importing BmpImagePlugin
2025-06-09 15:30:39,506 - PIL.Image - DEBUG - Importing BufrStubImagePlugin
2025-06-09 15:30:39,510 - PIL.Image - DEBUG - Importing CurImagePlugin
2025-06-09 15:30:39,517 - PIL.Image - DEBUG - Importing DcxImagePlugin
2025-06-09 15:30:39,522 - PIL.Image - DEBUG - Importing DdsImagePlugin
2025-06-09 15:30:39,560 - PIL.Image - DEBUG - Importing EpsImagePlugin
2025-06-09 15:30:39,572 - PIL.Image - DEBUG - Importing FitsImagePlugin
2025-06-09 15:30:39,579 - PIL.Image - DEBUG - Importing FliImagePlugin
2025-06-09 15:30:39,583 - PIL.Image - DEBUG - Importing FpxImagePlugin
2025-06-09 15:30:39,587 - PIL.Image - DEBUG - Image: failed to import FpxImagePlugin: No module named 'olefile'
2025-06-09 15:30:39,593 - PIL.Image - DEBUG - Importing FtexImagePlugin
2025-06-09 15:30:39,667 - PIL.Image - DEBUG - Importing GbrImagePlugin
2025-06-09 15:30:39,678 - PIL.Image - DEBUG - Importing GifImagePlugin
2025-06-09 15:30:39,679 - PIL.Image - DEBUG - Importing GribStubImagePlugin
2025-06-09 15:30:39,684 - PIL.Image - DEBUG - Importing Hdf5StubImagePlugin
2025-06-09 15:30:39,687 - PIL.Image - DEBUG - Importing IcnsImagePlugin
2025-06-09 15:30:39,697 - PIL.Image - DEBUG - Importing IcoImagePlugin
2025-06-09 15:30:39,708 - PIL.Image - DEBUG - Importing ImImagePlugin
2025-06-09 15:30:39,716 - PIL.Image - DEBUG - Importing ImtImagePlugin
2025-06-09 15:30:39,724 - PIL.Image - DEBUG - Importing IptcImagePlugin
2025-06-09 15:30:39,736 - PIL.Image - DEBUG - Importing JpegImagePlugin
2025-06-09 15:30:39,741 - PIL.Image - DEBUG - Importing Jpeg2KImagePlugin
2025-06-09 15:30:39,787 - PIL.Image - DEBUG - Importing McIdasImagePlugin
2025-06-09 15:30:39,792 - PIL.Image - DEBUG - Importing MicImagePlugin
2025-06-09 15:30:39,797 - PIL.Image - DEBUG - Image: failed to import MicImagePlugin: No module named 'olefile'
2025-06-09 15:30:39,798 - PIL.Image - DEBUG - Importing MpegImagePlugin
2025-06-09 15:30:39,801 - PIL.Image - DEBUG - Importing MpoImagePlugin
2025-06-09 15:30:39,826 - PIL.Image - DEBUG - Importing MspImagePlugin
2025-06-09 15:30:39,854 - PIL.Image - DEBUG - Importing PalmImagePlugin
2025-06-09 15:30:39,863 - PIL.Image - DEBUG - Importing PcdImagePlugin
2025-06-09 15:30:39,865 - PIL.Image - DEBUG - Importing PcxImagePlugin
2025-06-09 15:30:39,866 - PIL.Image - DEBUG - Importing PdfImagePlugin
2025-06-09 15:30:39,904 - PIL.Image - DEBUG - Importing PixarImagePlugin
2025-06-09 15:30:39,907 - PIL.Image - DEBUG - Importing PngImagePlugin
2025-06-09 15:30:39,908 - PIL.Image - DEBUG - Importing PpmImagePlugin
2025-06-09 15:30:39,908 - PIL.Image - DEBUG - Importing PsdImagePlugin
2025-06-09 15:30:39,912 - PIL.Image - DEBUG - Importing QoiImagePlugin
2025-06-09 15:30:39,916 - PIL.Image - DEBUG - Importing SgiImagePlugin
2025-06-09 15:30:39,919 - PIL.Image - DEBUG - Importing SpiderImagePlugin
2025-06-09 15:30:39,923 - PIL.Image - DEBUG - Importing SunImagePlugin
2025-06-09 15:30:39,925 - PIL.Image - DEBUG - Importing TgaImagePlugin
2025-06-09 15:30:39,928 - PIL.Image - DEBUG - Importing TiffImagePlugin
2025-06-09 15:30:39,931 - PIL.Image - DEBUG - Importing WebPImagePlugin
2025-06-09 15:30:39,951 - PIL.Image - DEBUG - Importing WmfImagePlugin
2025-06-09 15:30:39,954 - PIL.Image - DEBUG - Importing XbmImagePlugin
2025-06-09 15:30:39,958 - PIL.Image - DEBUG - Importing XpmImagePlugin
2025-06-09 15:30:39,961 - PIL.Image - DEBUG - Importing XVThumbImagePlugin
2025-06-09 15:30:39,969 - PIL.PngImagePlugin - DEBUG - STREAM b'IHDR' 161894 13
2025-06-09 15:30:39,971 - PIL.PngImagePlugin - DEBUG - STREAM b'orNT' 161919 1
2025-06-09 15:30:39,972 - PIL.PngImagePlugin - DEBUG - b'orNT' 161919 1 (unknown)
2025-06-09 15:30:39,973 - PIL.PngImagePlugin - DEBUG - STREAM b'IDAT' 161932 32768
2025-06-09 15:30:39,999 - haassist - INFO - Loaded tray icon: C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\img\icon.ico
2025-06-09 15:30:40,013 - haassist - INFO - System tray icon created
2025-06-09 15:30:40,020 - haassist - INFO - System tray started
2025-06-09 15:30:40,227 - haassist - INFO - Wake word using default microphone: Microphone (Intel SST Audio Dev
2025-06-09 15:30:40,357 - haassist - INFO - Audio stream initialized for wake word detection
2025-06-09 15:30:40,359 - haassist - INFO -  Wake word detection started
2025-06-09 15:30:40,360 - haassist - INFO -  Wake word detection started
2025-06-09 15:30:40,368 - haassist - DEBUG - Wake word detection thread priority lowered
2025-06-09 15:30:40,369 - haassist - INFO - Wake word detection loop started
2025-06-09 15:30:40,376 - haassist - INFO - Starting interface...
2025-06-09 15:30:42,685 - haassist - INFO - Attempting to hide window from taskbar...
2025-06-09 15:30:42,734 - haassist - WARNING - Failed to hide window from taskbar
[pywebview] Using WinForms / Chromium
2025-06-09 15:30:47,250 - pywebview - DEBUG - Using WinForms / Chromium
[pywebview] HTTP server root path: C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\frontend
2025-06-09 15:30:48,244 - pywebview - DEBUG - HTTP server root path: C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\frontend
Bottle v0.13.3 server starting up (using ThreadedAdapter())...
Listening on http://127.0.0.1:6535/
Hit Ctrl-C to quit.

127.0.0.1 - - [09/Jun/2025 15:31:10] "GET /index.html HTTP/1.1" 200 24012
127.0.0.1 - - [09/Jun/2025 15:31:12] "GET /.well-known/appspecific/com.chrome.devtools.json HTTP/1.1" 404 770
2025-06-09 15:31:14,694 - websockets.server - DEBUG - = connection is CONNECTING
[pywebview] before_load event fired. injecting pywebview object
2025-06-09 15:31:14,806 - pywebview - DEBUG - before_load event fired. injecting pywebview object
127.0.0.1 - - [09/Jun/2025 15:31:14] "GET /favicon.ico HTTP/1.1" 404 733
2025-06-09 15:31:15,134 - websockets.server - DEBUG - < GET / HTTP/1.1
2025-06-09 15:31:15,135 - websockets.server - DEBUG - < Host: localhost:8765
[pywebview] Loading JS files from C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\webview\js
2025-06-09 15:31:15,170 - websockets.server - DEBUG - < Connection: Upgrade
2025-06-09 15:31:15,120 - pywebview - DEBUG - Loading JS files from C:\Users\mahzi\AppData\Local\GLaSSIST\_internal\webview\js
2025-06-09 15:31:15,215 - websockets.server - DEBUG - < Pragma: no-cache
2025-06-09 15:31:15,255 - websockets.server - DEBUG - < Cache-Control: no-cache
2025-06-09 15:31:15,285 - websockets.server - DEBUG - < User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/137.0.0.0 Safari/537.36 Edg/137.0.0.0
2025-06-09 15:31:15,286 - websockets.server - DEBUG - < Upgrade: websocket
2025-06-09 15:31:15,288 - websockets.server - DEBUG - < Origin: http://127.0.0.1:6535
2025-06-09 15:31:15,290 - websockets.server - DEBUG - < Sec-WebSocket-Version: 13
2025-06-09 15:31:15,295 - websockets.server - DEBUG - < Accept-Encoding: gzip, deflate, br, zstd
2025-06-09 15:31:15,336 - websockets.server - DEBUG - < Accept-Language: en-US,en;q=0.9
2025-06-09 15:31:15,464 - websockets.server - DEBUG - < Sec-WebSocket-Key: FYK5dcQRJnrG1nFcj3LzQg==
2025-06-09 15:31:15,525 - websockets.server - DEBUG - < Sec-WebSocket-Extensions: permessage-deflate; client_max_window_bits
2025-06-09 15:31:15,692 - websockets.server - DEBUG - > HTTP/1.1 101 Switching Protocols
2025-06-09 15:31:17,594 - websockets.server - DEBUG - > Date: Mon, 09 Jun 2025 12:01:15 GMT
2025-06-09 15:31:17,992 - websockets.server - DEBUG - > Upgrade: websocket
2025-06-09 15:31:17,992 - websockets.server - DEBUG - > Connection: Upgrade
2025-06-09 15:31:17,994 - websockets.server - DEBUG - > Sec-WebSocket-Accept: /zMtz2lBuQ688wFvthO9eEkGsO4=
2025-06-09 15:31:17,996 - websockets.server - DEBUG - > Sec-WebSocket-Extensions: permessage-deflate; server_max_window_bits=12; client_max_window_bits=12
2025-06-09 15:31:17,996 - websockets.server - DEBUG - > Server: Python/3.13 websockets/15.0.1
2025-06-09 15:31:17,997 - websockets.server - DEBUG - = connection is OPEN
2025-06-09 15:31:17,998 - websockets.server - INFO - connection open
2025-06-09 15:31:18,061 - haassist - INFO - New animation client connected: ('::1', 52260, 0, 0)
2025-06-09 15:31:18,267 - websockets.server - DEBUG - > TEXT '{"type": "state_change", "state": "hidden"}' [43 bytes]
2025-06-09 15:31:19,607 - websockets.server - DEBUG - < TEXT '{"type":"ready"}' [16 bytes]
2025-06-09 15:31:19,817 - haassist - INFO - Animation client ready
[pywebview] _pywebviewready event fired
2025-06-09 15:31:20,672 - pywebview - DEBUG - _pywebviewready event fired
[pywebview] loaded event fired
2025-06-09 15:31:20,728 - pywebview - DEBUG - loaded event fired
2025-06-09 15:31:42,925 - websockets.server - DEBUG - < TEXT '{"type":"ping"}' [15 bytes]
2025-06-09 15:31:42,926 - websockets.server - DEBUG - > TEXT '{"type": "pong"}' [16 bytes]
2025-06-09 15:32:12,953 - websockets.server - DEBUG - < TEXT '{"type":"ping"}' [15 bytes]
2025-06-09 15:32:12,965 - websockets.server - DEBUG - > TEXT '{"type": "pong"}' [16 bytes]
2025-06-09 15:32:43,081 - websockets.server - DEBUG - < TEXT '{"type":"ping"}' [15 bytes]
2025-06-09 15:32:43,152 - websockets.server - DEBUG - > TEXT '{"type": "pong"}' [16 bytes]
2025-06-09 15:32:52,082 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.998)
2025-06-09 15:32:52,095 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.998)
2025-06-09 15:32:52,198 - asyncio - DEBUG - Using proactor: IocpProactor
2025-06-09 15:32:52,457 - haassist - INFO - Animation state change: hidden -> listening
2025-06-09 15:32:52,519 - websockets.server - DEBUG - > TEXT '{"type": "state_change", "state": "listening", ...estamp": 1749470572463}' [74 bytes]
2025-06-09 15:32:52,709 - haassist - INFO - VAD initialized: mode=3, silence threshold=1.5s, chunk size=480
2025-06-09 15:32:52,717 - haassist - INFO - AudioManager initialized: 16000Hz, 1 channel(s), chunk 480
2025-06-09 15:32:52,727 - haassist - INFO - Checking pipeline availability: 01jwxm9q3b75syrws84ycvwvxz
2025-06-09 15:32:52,792 - haassist - DEBUG - Audio device 0: Microsoft Sound Mapper - Input - input channels: 2
2025-06-09 15:32:52,802 - haassist - INFO - Found microphone: Microsoft Sound Mapper - Input
2025-06-09 15:32:52,803 - haassist - DEBUG - Audio device 1: Microphone (Intel SST Audio Dev - input channels: 2
2025-06-09 15:32:52,805 - haassist - INFO - Found default microphone: Microphone (Intel SST Audio Dev
2025-06-09 15:32:52,806 - haassist - DEBUG - Audio device 2: Microsoft Sound Mapper - Output - input channels: 0
2025-06-09 15:32:52,807 - haassist - DEBUG - Audio device 3: Speakers/Headphones (Intel SST  - input channels: 0
2025-06-09 15:32:52,812 - haassist - DEBUG - Audio device 4: Primary Sound Capture Driver - input channels: 2
2025-06-09 15:32:52,813 - haassist - DEBUG - Audio device 5: Microphone (Intel SST Audio Device (WDM)) - input channels: 2
2025-06-09 15:32:52,814 - haassist - DEBUG - Audio device 6: Primary Sound Driver - input channels: 0
2025-06-09 15:32:52,818 - haassist - DEBUG - Audio device 7: Speakers/Headphones (Intel SST Audio Device (WDM)) - input channels: 0
2025-06-09 15:32:52,826 - haassist - DEBUG - Audio device 8: Speakers/Headphones (Intel SST Audio Device (WDM)) - input channels: 0
2025-06-09 15:32:52,827 - haassist - DEBUG - Audio device 9: Microphone (Intel SST Audio Device (WDM)) - input channels: 2
2025-06-09 15:32:52,833 - haassist - DEBUG - Audio device 10: Speakers (IntelSST Audio Wave for IHF) - input channels: 0
2025-06-09 15:32:52,834 - haassist - DEBUG - Audio device 11: Microphone (IntelSST Audio Wave for DMIC) - input channels: 2
2025-06-09 15:32:53,047 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.997)
2025-06-09 15:32:53,051 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.997)
2025-06-09 15:32:53,052 - haassist - INFO - Application is busy, ignoring wake word
2025-06-09 15:32:53,338 - haassist - INFO - Audio stream initialized: 16000 Hz, 1 channel(s), chunk 480
2025-06-09 15:32:53,433 - haassist - INFO - Connecting to Home Assistant: ws://192.168.31.58:8123/api/websocket
2025-06-09 15:32:54,205 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.995)
2025-06-09 15:32:54,223 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.995)
2025-06-09 15:32:54,225 - haassist - INFO - Application is busy, ignoring wake word
2025-06-09 15:33:05,096 - websockets.client - DEBUG - = connection is CONNECTING
2025-06-09 15:33:05,958 - websockets.client - DEBUG - > GET /api/websocket HTTP/1.1
2025-06-09 15:33:06,110 - websockets.client - DEBUG - > Host: 192.168.31.58:8123
2025-06-09 15:33:06,307 - websockets.client - DEBUG - > Upgrade: websocket
2025-06-09 15:33:06,654 - websockets.client - DEBUG - > Connection: Upgrade
2025-06-09 15:33:06,836 - websockets.client - DEBUG - > Sec-WebSocket-Key: KOOOoY6JzBd/6qKNqNnLHQ==
2025-06-09 15:33:06,976 - websockets.client - DEBUG - > Sec-WebSocket-Version: 13
2025-06-09 15:33:06,977 - websockets.client - DEBUG - > Sec-WebSocket-Extensions: permessage-deflate; client_max_window_bits
2025-06-09 15:33:07,020 - websockets.client - DEBUG - > User-Agent: Python/3.13 websockets/15.0.1
2025-06-09 15:33:07,389 - websockets.client - DEBUG - < HTTP/1.1 101 Switching Protocols
2025-06-09 15:33:07,391 - websockets.client - DEBUG - < Upgrade: websocket
2025-06-09 15:33:07,392 - websockets.client - DEBUG - < Connection: upgrade
2025-06-09 15:33:07,562 - websockets.client - DEBUG - < Sec-WebSocket-Accept: AV/KGQGtrwhjTL4nq3GsTIo+Fhg=
2025-06-09 15:33:07,576 - websockets.client - DEBUG - < Sec-WebSocket-Extensions: permessage-deflate
2025-06-09 15:33:07,576 - websockets.client - DEBUG - < Date: Mon, 09 Jun 2025 12:03:07 GMT
2025-06-09 15:33:07,577 - websockets.client - DEBUG - < Server: Python/3.13 aiohttp/3.11.18
2025-06-09 15:33:07,636 - websockets.client - DEBUG - = connection is OPEN
2025-06-09 15:33:07,752 - websockets.client - DEBUG - < TEXT '{"type":"auth_required","ha_version":"2025.5.3"}' [48 bytes]
2025-06-09 15:33:07,781 - haassist - INFO - Connection established
2025-06-09 15:33:07,792 - websockets.client - DEBUG - > TEXT '{"type": "auth", "access_token": "eyJhbGciOiJIU...uR1mlnoPtZOKCmtJLgTlw"}' [219 bytes]
2025-06-09 15:33:07,825 - websockets.client - DEBUG - < TEXT '{"type":"auth_ok","ha_version":"2025.5.3"}' [42 bytes]
2025-06-09 15:33:07,828 - haassist - INFO - Authentication completed successfully
2025-06-09 15:33:07,869 - haassist - INFO - šŸ” Fetching Assist pipelines...
2025-06-09 15:33:07,876 - websockets.client - DEBUG - > TEXT '{"id": 1, "type": "assist_pipeline/pipeline/list"}' [50 bytes]
2025-06-09 15:33:07,994 - websockets.client - DEBUG - < TEXT '{"id":1,"type":"result","success":true,"result"...9q3b75syrws84ycvwvxz"}}' [834 bytes]
2025-06-09 15:33:07,997 - haassist - INFO - āœ… Found 2 pipelines
2025-06-09 15:33:07,999 - haassist - INFO - šŸ† Preferred pipeline: 01jwxm9q3b75syrws84ycvwvxz
2025-06-09 15:33:08,006 - haassist - INFO -   šŸ“‹ Home Assistant
2025-06-09 15:33:08,007 - haassist - INFO -       ID: 01jwxhv3mv8h2zg2vvpteftva8
2025-06-09 15:33:08,008 - haassist - INFO -       Language: en
2025-06-09 15:33:08,008 - haassist - INFO -       Conversation: conversation.home_assistant
2025-06-09 15:33:08,009 - haassist - INFO -       STT: None
2025-06-09 15:33:08,010 - haassist - INFO -       TTS: None (None)
2025-06-09 15:33:08,011 - haassist - INFO -   šŸ“‹ Local sst and tts ā­ (PREFERRED)
2025-06-09 15:33:08,013 - haassist - INFO -       ID: 01jwxm9q3b75syrws84ycvwvxz
2025-06-09 15:33:08,014 - haassist - INFO -       Language: en
2025-06-09 15:33:08,015 - haassist - INFO -       Conversation: conversation.home_assistant
2025-06-09 15:33:08,016 - haassist - INFO -       STT: stt.speech_to_phrase
2025-06-09 15:33:08,017 - haassist - INFO -       TTS: tts.piper (en_US-amy-low)
2025-06-09 15:33:08,019 - haassist - INFO - šŸ LOADED 2 PIPELINES
2025-06-09 15:33:08,020 - haassist - INFO - Connected to Home Assistant
2025-06-09 15:33:08,026 - haassist - INFO - Starting Assist pipeline
2025-06-09 15:33:08,027 - haassist - INFO - Using pipeline ID: 01jwxm9q3b75syrws84ycvwvxz
2025-06-09 15:33:08,028 - websockets.client - DEBUG - > TEXT '{"id": 2, "type": "assist_pipeline/run", "start...m9q3b75syrws84ycvwvxz"}' [172 bytes]
2025-06-09 15:33:08,240 - websockets.client - DEBUG - < TEXT '{"id":2,"type":"result","success":true,"result":null}' [53 bytes]
2025-06-09 15:33:08,243 - websockets.client - DEBUG - < TEXT '{"id":2,"type":"event","event":{"type":"run-sta...2:03:08.516178+00:00"}}' [393 bytes]
2025-06-09 15:33:08,246 - haassist - INFO - Received: {'id': 2, 'type': 'result', 'success': True, 'result': None}
2025-06-09 15:33:08,273 - haassist - INFO - Received: {'id': 2, 'type': 'event', 'event': {'type': 'run-start', 'data': {'pipeline': '01jwxm9q3b75syrws84ycvwvxz', 'language': 'en', 'conversation_id': '01JXA95BJJ1SGHNQADWA1P3W4R', 'runner_data': {'stt_binary_handler_id': 1, 'timeout': 30}, 'tts_output': {'token': 'n8sKkkBvrdNKjgjErRwuXw.mp3', 'url': '/api/tts_proxy/n8sKkkBvrdNKjgjErRwuXw.mp3', 'mime_type': 'audio/mpeg'}}, 'timestamp': '2025-06-09T12:03:08.516178+00:00'}}
2025-06-09 15:33:08,276 - haassist - INFO - Received stt_binary_handler_id: 1
2025-06-09 15:33:08,307 - haassist - INFO - Saved audio URL from run-start: /api/tts_proxy/n8sKkkBvrdNKjgjErRwuXw.mp3
2025-06-09 15:33:08,308 - haassist - INFO - Assist pipeline started successfully

=== LISTENING ===
(Waiting for voice, speak to microphone...)
2025-06-09 15:33:08,758 - haassist - INFO - Starting recording with VAD detection
2025-06-09 15:33:08,784 - haassist - INFO - Speech start detected
2025-06-09 15:33:08,786 - haassist - INFO - Started speech processing
2025-06-09 15:33:09,803 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.182983346...estamp": 1749470589610}' [740 bytes]
2025-06-09 15:33:09,844 - websockets.client - DEBUG - > BINARY 01 87 ff 5d ff 5b ff 57 ff 5c ff 62 ff 30 ff 13 ... 00 fe 27 fe 61 fe 33 fe [961 bytes]
2025-06-09 15:33:09,943 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.230143013...estamp": 1749470589936}' [725 bytes]
2025-06-09 15:33:09,953 - websockets.client - DEBUG - > BINARY 01 0b fe 01 fe 12 fe 54 fe 53 fe 66 fe 8b fe a7 ... 32 00 2e 00 42 00 5e 00 [961 bytes]
2025-06-09 15:33:09,998 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.100828611...estamp": 1749470589994}' [737 bytes]
2025-06-09 15:33:10,012 - websockets.client - DEBUG - > BINARY 01 81 00 68 00 5f 00 3f 00 3d 00 28 00 21 00 2e ... bf fe d0 fe e8 fe f8 fe [961 bytes]
2025-06-09 15:33:10,060 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.347077493...estamp": 1749470590058}' [730 bytes]
2025-06-09 15:33:10,062 - websockets.client - DEBUG - > BINARY 01 0a ff 1a ff 02 ff f2 fe 1b ff 39 ff 4a ff 46 ... eb 00 d6 00 d8 00 f7 00 [961 bytes]
2025-06-09 15:33:10,136 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.108832975...estamp": 1749470590134}' [743 bytes]
2025-06-09 15:33:10,172 - websockets.client - DEBUG - > BINARY 01 31 01 3c 01 47 01 6e 01 9d 01 d2 01 0a 02 34 ... 81 ff 8a ff 7a ff 7d ff [961 bytes]
2025-06-09 15:33:10,318 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.251934877...estamp": 1749470590317}' [731 bytes]
2025-06-09 15:33:10,321 - websockets.client - DEBUG - > BINARY 01 62 00 8d 00 cb 00 eb 00 ff 00 44 01 6e 01 5f ... 14 01 15 01 1b 01 40 01 [961 bytes]
2025-06-09 15:33:10,592 - websockets.client - DEBUG - > BINARY 01 50 fe 51 fe 37 fe f9 fd f8 fd 13 fe fe fd f0 ... 2f 02 5c 02 79 02 8d 02 [961 bytes]
2025-06-09 15:33:10,743 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.217600124...estamp": 1749470590592}' [730 bytes]
2025-06-09 15:33:10,772 - websockets.client - DEBUG - > BINARY 01 c1 fd ad fd b5 fd c1 fd aa fd 7a fd 7f fd 8d ... 53 ff 65 ff 6e ff 77 ff [961 bytes]
2025-06-09 15:33:10,827 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.211456420...estamp": 1749470590771}' [731 bytes]
2025-06-09 15:33:10,894 - websockets.client - DEBUG - > BINARY 01 06 00 11 00 1f 00 00 00 f0 ff d8 ff d5 ff f2 ... d6 fc e2 fc e9 fc e8 fc [961 bytes]
2025-06-09 15:33:10,903 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.158195531...estamp": 1749470590894}' [731 bytes]
2025-06-09 15:33:11,089 - websockets.client - DEBUG - > BINARY 01 90 03 99 03 88 03 8d 03 a0 03 b6 03 fe 03 29 ... 91 fe 96 fe 90 fe 88 fe [961 bytes]
2025-06-09 15:33:11,092 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.183739305...estamp": 1749470591088}' [728 bytes]
2025-06-09 15:33:11,102 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.206273294...estamp": 1749470591099}' [729 bytes]
2025-06-09 15:33:11,103 - websockets.client - DEBUG - > BINARY 01 14 00 d5 ff b0 ff cd ff d6 ff e0 ff 01 00 f7 ... 9c 00 b2 00 d3 00 ef 00 [961 bytes]
2025-06-09 15:33:11,208 - websockets.client - DEBUG - > BINARY 01 0d 01 f0 00 dc 00 e3 00 e1 00 f2 00 ee 00 e4 ... f7 fd df fd d6 fd c6 fd [961 bytes]
2025-06-09 15:33:11,210 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.216625267...estamp": 1749470591207}' [733 bytes]
2025-06-09 15:33:11,217 - websockets.client - DEBUG - > BINARY 01 73 fe a1 fe bb fe c0 fe bf fe 9c fe 97 fe 8a ... 6d ff 78 ff 64 ff 4b ff [961 bytes]
2025-06-09 15:33:11,322 - websockets.client - DEBUG - > BINARY 01 8b 01 7d 01 76 01 9a 01 a8 01 9f 01 aa 01 8f ... f0 fe e4 fe dc fe ca fe [961 bytes]
2025-06-09 15:33:11,366 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.091454123...estamp": 1749470591216}' [747 bytes]
2025-06-09 15:33:11,368 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.316779844...estamp": 1749470591322}' [733 bytes]
2025-06-09 15:33:11,402 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.160971806...estamp": 1749470591401}' [746 bytes]
2025-06-09 15:33:11,403 - websockets.client - DEBUG - > BINARY 01 f2 fe 07 ff ff fe 0a ff 21 ff 41 ff 6a ff 7b ... 7c fe 7e fe a2 fe c3 fe [961 bytes]
2025-06-09 15:33:11,684 - haassist - INFO - Speech end detected after 1.69s silence
2025-06-09 15:33:11,700 - websockets.client - DEBUG - > BINARY 01 cc ff cf ff b3 ff 9c ff c1 ff d2 ff a4 ff 5d ... ef 02 d8 02 f3 02 da 02 [961 bytes]
2025-06-09 15:33:11,918 - websockets.server - DEBUG - > TEXT '{"type": "audio_data", "fft": [1.0, 0.226233480...estamp": 1749470591700}' [732 bytes]
2025-06-09 15:33:11,950 - haassist - INFO - Recording completed after 3.2s, processed 16 chunks
2025-06-09 15:33:11,985 - haassist - INFO - === SWITCHING TO PROCESSING ===
2025-06-09 15:33:11,987 - haassist - INFO - Animation state change: listening -> processing
2025-06-09 15:33:11,989 - websockets.server - DEBUG - > TEXT '{"type": "state_change", "state": "processing",...estamp": 1749470591987}' [75 bytes]
2025-06-09 15:33:12,001 - websockets.client - DEBUG - < TEXT '{"id":2,"type":"event","event":{"type":"stt-sta...2:03:08.519941+00:00"}}' [244 bytes]
2025-06-09 15:33:12,849 - haassist - INFO - Sending end of audio signal
2025-06-09 15:33:12,895 - websockets.client - DEBUG - > BINARY 01 [1 byte]
2025-06-09 15:33:12,951 - websockets.server - DEBUG - < TEXT '{"type":"ping"}' [15 bytes]
2025-06-09 15:33:13,012 - websockets.server - DEBUG - > TEXT '{"type": "pong"}' [16 bytes]
2025-06-09 15:33:13,016 - haassist - INFO - Recording completed
2025-06-09 15:33:13,093 - haassist - INFO - Audio sent successfully
2025-06-09 15:33:13,098 - haassist - INFO - === RECEIVING RESPONSE ===
2025-06-09 15:33:13,241 - haassist - INFO - Received: {'id': 2, 'type': 'event', 'event': {'type': 'stt-start', 'data': {'engine': 'stt.speech_to_phrase', 'metadata': {'language': 'en', 'format': 'wav', 'codec': 'pcm', 'bit_rate': 16, 'sample_rate': 16000, 'channel': 1}}, 'timestamp': '2025-06-09T12:03:08.519941+00:00'}}
2025-06-09 15:33:25,805 - websockets.client - DEBUG - < TEXT '{"id":2,"type":"event","event":{"type":"error",...2:03:26.099957+00:00"}}' [167 bytes]
2025-06-09 15:33:25,806 - haassist - INFO - Received: {'id': 2, 'type': 'event', 'event': {'type': 'error', 'data': {'code': 'stt-no-text-recognized', 'message': 'No text recognized'}, 'timestamp': '2025-06-09T12:03:26.099957+00:00'}}
2025-06-09 15:33:25,865 - haassist - INFO - Ending reception on event: error

=== ASSISTANT ERROR ===
Error: stt-no-text-recognized - No text recognized
===========================

2025-06-09 15:33:26,023 - haassist - INFO - Animation state change: processing -> error
2025-06-09 15:33:26,121 - haassist - INFO - Error message: No words detected. Try again.
2025-06-09 15:33:26,163 - websockets.server - DEBUG - > TEXT '{"type": "state_change", "state": "error", "tim... detected. Try again."}' [119 bytes]
2025-06-09 15:33:26,168 - websockets.client - DEBUG - < TEXT '{"id":2,"type":"event","event":{"type":"run-end...2:03:26.101154+00:00"}}' [109 bytes]
2025-06-09 15:33:27,891 - websockets.client - DEBUG - > PING 28 cd 78 a3 [binary, 4 bytes]
2025-06-09 15:33:27,986 - websockets.client - DEBUG - % sent keepalive ping
2025-06-09 15:33:28,137 - websockets.client - DEBUG - < PONG 28 cd 78 a3 [binary, 4 bytes]
2025-06-09 15:33:28,141 - websockets.client - DEBUG - % received keepalive pong
2025-06-09 15:33:31,499 - haassist - INFO - Animation state change: error -> hidden
2025-06-09 15:33:31,512 - websockets.server - DEBUG - > TEXT '{"type": "state_change", "state": "hidden", "timestamp": 1749470611501}' [71 bytes]
2025-06-09 15:33:31,817 - haassist - INFO - Cleaning up voice command session...
2025-06-09 15:33:32,481 - haassist - INFO - Audio stream closed
2025-06-09 15:33:32,497 - haassist - INFO - PyAudio terminated
2025-06-09 15:33:32,498 - haassist - DEBUG - Temp audio manager closed
2025-06-09 15:33:32,638 - websockets.client - DEBUG - > CLOSE 1000 (OK) [2 bytes]
2025-06-09 15:33:32,654 - websockets.client - DEBUG - = connection is CLOSING
2025-06-09 15:33:32,698 - websockets.client - DEBUG - < CLOSE 1000 (OK) [2 bytes]
2025-06-09 15:33:32,705 - websockets.client - DEBUG - < EOF
2025-06-09 15:33:32,708 - websockets.client - DEBUG - > EOF
2025-06-09 15:33:32,709 - websockets.client - DEBUG - = connection is CLOSED
2025-06-09 15:33:32,710 - websockets.client - DEBUG - x half-closing TCP connection
2025-06-09 15:33:32,724 - haassist - INFO - Connection closed
2025-06-09 15:33:32,725 - haassist - DEBUG - Temp HA client closed
2025-06-09 15:33:32,726 - haassist - INFO - Voice command session cleanup completed
2025-06-09 15:33:42,926 - websockets.server - DEBUG - < TEXT '{"type":"ping"}' [15 bytes]
2025-06-09 15:33:42,932 - websockets.server - DEBUG - > TEXT '{"type": "pong"}' [16 bytes]
2025-06-09 15

I canā€™t get it to work voice control using the mic on the surface tablet (which the HA server is on it). but my android phone is working fine. that means stt tts are ok on server

do you have anydesk?

32

Ok, new release - debug and normal version

I added new button in ā€œAdvancedā€ tab of settings
image

I did some testing, and here are results:

image
image653Ɨ241 9.67 KB

1 Like
33

you did it man. Thank you

I need to mention few things

  1. app is awefuuly slow at first run but in next runs itā€™s ok
  2. it stutter to answer. like this: computer, turn on light. answer: tuuuuurrrrnneed onn the switch
  3. when I click ā€œpause wake wordā€ I get this error
2025-06-11 14:31:05,014 - haassist - INFO - Stopping wake word detection...
2025-06-11 14:31:05,082 - haassist - INFO - Wake word detection loop ended
2025-06-11 14:31:05,113 - haassist - INFO - Wake word detection stopped
2025-06-11 14:31:05,113 - haassist - INFO - Wake word detection stopped
 Wake word detection paused
2025-06-11 14:31:05,114 - haassist - ERROR - Wake word paused
2025-06-11 14:31:05,115 - haassist - DEBUG - State change: hidden -> error

and after ā€œresume wake wordā€

2025-06-11 14:35:14,257 - haassist - INFO - Wake word using selected microphone: Microphone (Intel SST Audio Dev
2025-06-11 14:35:14,302 - haassist - INFO - Audio stream initialized for wake word detection
2025-06-11 14:35:14,316 - haassist - INFO -  Wake word detection started
2025-06-11 14:35:14,317 - haassist - INFO -  Wake word detection started
 Wake word detection resumed
2025-06-11 14:35:14,318 - haassist - DEBUG - Wake word detection thread priority lowered
2025-06-11 14:35:14,319 - haassist - INFO - Wake word resumed
2025-06-11 14:35:14,319 - haassist - INFO - Wake word detection loop started
2025-06-11 14:35:14,320 - haassist - DEBUG - State change: error -> success
2025-06-11 14:35:55,293 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.879)
2025-06-11 14:35:55,294 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.879)
2025-06-11 14:35:55,294 - haassist - INFO - Application is busy, ignoring wake word
2025-06-11 14:35:55,838 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.998)
2025-06-11 14:35:55,839 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.998)
2025-06-11 14:35:55,839 - haassist - INFO - Application is busy, ignoring wake word
2025-06-11 14:35:56,386 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.999)
2025-06-11 14:35:56,387 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.999)
2025-06-11 14:35:56,387 - haassist - INFO - Application is busy, ignoring wake word
2025-06-11 14:35:56,931 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.998)
2025-06-11 14:35:56,932 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.998)
2025-06-11 14:35:56,933 - haassist - INFO - Application is busy, ignoring wake word
2025-06-11 14:35:57,478 - haassist - INFO - Wake word detected: 'computer_v2' (confidence: 0.997)
2025-06-11 14:35:57,479 - haassist - INFO -  Wake word 'computer_v2' detected (confidence: 0.997)
2025-06-11 14:35:57,479 - haassist - INFO - Application is busy, ignoring wake word

and activate word (ctrl+shift+g) doesnā€™t work either

2025-06-11 14:37:53,325 - haassist - INFO - Voice command activation from tray menu
2025-06-11 14:37:53,326 - haassist - INFO - Application is busy, ignoring trigger
1 Like
34 
2025-06-11 14:31:05,114 - haassist - ERROR - Wake word paused
2025-06-11 14:31:05,115 - haassist - DEBUG - State change: hidden -> error

That is my way to showing red circle to user :wink: No error here, no worries. I wasnā€™t implementing state ā€œdisabledā€ or something, just raised existing error logic for that. Same with success on ā€œresume wake wordā€

2025-06-11 14:37:53,325 - haassist - INFO - Voice command activation from tray menu
2025-06-11 14:37:53,326 - haassist - INFO - Application is busy, ignoring trigger

And this is propably because application is already in listening/processing/answering mode so it is ignoring next activation.

  1. it stutter to answer. like this: computer, turn on light. answer: tuuuuurrrrnneed onn the switch

for that i think i have no more ideas - application is not that heavy, wake word processing unfortunetely needs to take some resources. Maybe other python library for processing audio? No idea

35

whatever it is, resuming and activating manually doesnā€™t work after pause

1 Like
36

Oh sorry, i misunderstood your problem.

Man, you are best tester ever :wink:

Quick fix, i updated the files:

After enabling wake word you have to wait 3 seconds. I had to simulate animation server behaviour without animation server and forgot about changing states error/success to hidden. The app activates only when the state is hidden, fixed now so it should work as excepted.

1 Like
37

fixed, works great now

thanks
you took your time to code this and specially added some options for me, in return itā€™s the least I can do. Thank you

1 Like