pygpt-net 2.4.49__py3-none-any.whl → 2.4.50__py3-none-any.whl

CHANGELOG.md

@@ -1,5 +1,10 @@
 # CHANGELOG
 
+## 2.4.50 (2025-01-16)
+
+- Refactored audio input core.
+- Added audio input volume progress bar.
+
 ## 2.4.49 (2025-01-16)
 
 - Fix: stream render in Assistants mode.

README.md

@@ -2,7 +2,7 @@
 
 [![pygpt](https://snapcraft.io/pygpt/badge.svg)](https://snapcraft.io/pygpt)
 
-Release: **2.4.49** | build: **2025.01.16** | Python: **>=3.10, <3.13**
+Release: **2.4.50** | build: **2025.01.16** | Python: **>=3.10, <3.13**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -118,6 +118,7 @@ sudo snap connect pygpt:camera
 
 ```commandline
 sudo snap connect pygpt:audio-record :audio-record
+sudo snap connect pygpt:alsa
 ```
 
 **Connecting IPython in Docker in Snap version**:
@@ -3952,6 +3953,11 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**2.4.50 (2025-01-16)**
+
+- Refactored audio input core.
+- Added audio input volume progress bar.
+
 **2.4.49 (2025-01-16)**
 
 - Fix: stream render in Assistants mode.

pygpt_net/CHANGELOG.txt

@@ -1,3 +1,8 @@
+2.4.50 (2025-01-16)
+
+- Refactored audio input core.
+- Added audio input volume progress bar.
+
 2.4.49 (2025-01-16)
 
 - Fix: stream render in Assistants mode.

pygpt_net/__init__.py

@@ -6,14 +6,14 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.01.16 01:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 __author__ = "Marcin Szczygliński"
 __copyright__ = "Copyright 2025, Marcin Szczygliński"
 __credits__ = ["Marcin Szczygliński"]
 __license__ = "MIT"
-__version__ = "2.4.49"
+__version__ = "2.4.50"
 __build__ = "2025.01.16"
 __maintainer__ = "Marcin Szczygliński"
 __github__ = "https://github.com/szczyglis-dev/py-gpt"

pygpt_net/controller/access/voice.py

@@ -6,13 +6,11 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.14 08:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 from typing import Optional, List, Dict, Any
 
-import pyaudio
-import wave
 import os
 
 from PySide6.QtCore import QTimer, Slot
@@ -38,9 +36,6 @@ class Voice:
         """
         self.window = window
         self.is_recording = False
-        self.frames = []
-        self.p = None
-        self.stream = None
         self.timer = None
         self.input_file = "voice_control.wav"
         self.thread_started = False
@@ -218,15 +213,6 @@ class Voice:
 
     def start_recording(self):
         """Start recording"""
-        self.frames = []  # clear audio frames
-
-        def callback(in_data, frame_count, time_info, status):
-            self.frames.append(in_data)
-            if self.is_recording:
-                return (in_data, pyaudio.paContinue)
-            else:
-                return (in_data, pyaudio.paComplete)
-
         try:
             self.is_recording = True
             self.switch_btn_stop()
@@ -235,23 +221,26 @@ class Voice:
             if self.window.controller.audio.is_playing():
                 self.window.controller.audio.stop_output()
 
+            # set audio volume bar
+            self.window.core.audio.capture.set_bar(
+                self.window.ui.nodes['voice.control.btn'].bar
+            )
+
             # start timeout timer to prevent infinite recording
             if self.timer is None:
                 self.timer = QTimer()
                 self.timer.timeout.connect(self.stop_timeout)
                 self.timer.start(self.TIMEOUT_SECONDS * 1000)
 
-            self.p = pyaudio.PyAudio()
-            self.stream = self.p.open(format=pyaudio.paInt16,
-                                      channels=1,
-                                      rate=44100,
-                                      input=True,
-                                      frames_per_buffer=1024,
-                                      stream_callback=callback)
+            if not self.window.core.audio.capture.check_audio_input():
+                raise Exception("Audio input not working.")
+                # IMPORTANT!!!!
+                # Stop here if audio input not working!
+                # This prevents the app from freezing when audio input is not working!
 
+            self.window.core.audio.capture.start()  # start recording if audio is OK
             self.window.update_status(trans('audio.speak.now'))
             self.window.dispatch(AppEvent(AppEvent.VOICE_CONTROL_STARTED))  # app event
-            self.stream.start_stream()
         except Exception as e:
             self.is_recording = False
             self.window.core.debug.log(e)
@@ -270,35 +259,29 @@ class Voice:
 
         :param timeout: True if stopped due to timeout
         """
+        self.window.core.audio.capture.reset_audio_level()
         self.is_recording = False
         if self.timer:
             self.timer.stop()
             self.timer = None
         self.switch_btn_start()  # switch button to start
         path = os.path.join(self.window.core.config.path, self.input_file)
+        self.window.core.audio.capture.set_path(path)
 
-        if self.stream is not None:
-            self.stream.stop_stream()
-            self.stream.close()
-            self.p.terminate()
-
+        if self.window.core.audio.capture.has_source():
+            self.window.core.audio.capture.stop()  # stop recording
             # abort if timeout
             if timeout:
                 self.window.dispatch(AppEvent(AppEvent.VOICE_CONTROL_STOPPED))  # app event
                 self.window.update_status("Aborted.".format(self.TIMEOUT_SECONDS))
                 return
 
-            if self.frames:
-                if len(self.frames) < self.MIN_FRAMES:
+            if self.window.core.audio.capture.has_frames():
+                frames = self.window.core.audio.capture.get_frames()
+                if len(frames) < self.MIN_FRAMES:
                     self.window.update_status(trans("status.audio.too_short"))
                     self.window.dispatch(AppEvent(AppEvent.VOICE_CONTROL_STOPPED))  # app event
                     return
-                wf = wave.open(path, 'wb')
-                wf.setnchannels(1)
-                wf.setsampwidth(self.p.get_sample_size(pyaudio.paInt16))
-                wf.setframerate(44100)
-                wf.writeframes(b''.join(self.frames))
-                wf.close()
                 self.window.dispatch(AppEvent(AppEvent.VOICE_CONTROL_SENT))  # app event
                 self.handle_thread(True)  # handle transcription in simple mode
         else:

pygpt_net/core/audio/__init__.py

@@ -6,17 +6,19 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.14 18:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 import re
 from typing import Union, Optional, Tuple, List
 
+from PySide6.QtMultimedia import QMediaDevices
 from bs4 import UnicodeDammit
 
 from pygpt_net.provider.audio_input.base import BaseProvider as InputBaseProvider
 from pygpt_net.provider.audio_output.base import BaseProvider as OutputBaseProvider
 
+from .capture import Capture
 from .whisper import Whisper
 
 
@@ -28,6 +30,7 @@ class Audio:
         :param window: Window instance
         """
         self.window = window
+        self.capture = Capture(window)
         self.whisper = Whisper(window)
         self.providers = {
             "input": {},
@@ -41,21 +44,12 @@ class Audio:
 
         :return devices list: [(id, name)]
         """
-        import pyaudio
-        devices = []
-        try:
-            p = pyaudio.PyAudio()
-            num_devices = p.get_device_count()
-            for i in range(num_devices):
-                info = p.get_device_info_by_index(i)
-                if info["maxInputChannels"] > 0:
-                    dammit = UnicodeDammit(info["name"])
-                    devices.append((i, dammit.unicode_markup))
-                    # print(f"Device ID {i}: {info['name']}")
-            p.terminate()
-        except Exception as e:
-            print(f"Audio input devices receive error: {e}")
-        return devices
+        devices = QMediaDevices.audioInputs()
+        devices_list = []
+        for index, device in enumerate(devices):
+            dammit = UnicodeDammit(device.description())
+            devices_list.append((index, dammit.unicode_markup))
+        return devices_list
 
     def is_device_compatible(self, device_index: int) -> bool:
         """
@@ -69,7 +63,6 @@ class Audio:
         channels = int(self.window.core.config.get('audio.input.channels', 1))
         p = pyaudio.PyAudio()
         info = p.get_device_info_by_index(device_index)
-        supported = False
         try:
             p.is_format_supported(
                 rate=rate,

pygpt_net/core/audio/capture.py

@@ -0,0 +1,331 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+# ================================================== #
+# This file is a part of PYGPT package               #
+# Website: https://pygpt.net                         #
+# GitHub:  https://github.com/szczyglis-dev/py-gpt   #
+# MIT License                                        #
+# Created By  : Marcin Szczygliński                  #
+# Updated Date: 2025.01.16 17:00:00                  #
+# ================================================== #
+
+import numpy as np
+import wave
+
+from PySide6.QtMultimedia import QAudioFormat, QMediaDevices, QAudioSource
+
+class Capture:
+    def __init__(self, window=None):
+        """
+        Audio input capture core
+
+        :param window: Window instance
+        """
+        self.window = window
+        self.audio_source = None
+        self.audio_io_device = None
+        self.frames = []
+        self.actual_audio_format = None
+        self.path = None
+        self.disconnected = False
+        self.devices = []
+        self.selected_device = None
+        self.bar = None
+        self.check_audio_devices()
+
+    def set_path(self, path: str):
+        """
+        Set audio input file path
+
+        :param path: file path
+        """
+        self.path = path
+
+    def set_bar(self, bar):
+        """
+        Set audio level bar
+
+        :param bar: audio level bar
+        """
+        self.bar = bar
+
+    def check_audio_devices(self):
+        """Check audio input devices"""
+        self.devices = QMediaDevices.audioInputs()
+        if not self.devices:
+            # no devices found
+            self.selected_device = None
+            print("No audio input devices found.")
+        else:
+            # set the first device as default
+            self.selected_device = self.devices[0]
+
+    def device_changed(self, index: int):
+        """
+        Change audio input device
+
+        :param index: device index
+        """
+        if 0 <= index < len(self.devices):
+            self.selected_device = self.devices[index]
+        else:
+            self.selected_device = None
+
+    def prepare_device(self):
+        """Set the current audio input device"""
+        device_id = int(self.window.core.config.get('audio.input.device', 0))
+        self.device_changed(device_id)
+
+    def start(self):
+        """
+        Start audio input recording
+
+        :return: True if started
+        """
+        # Clear previous frames
+        self.frames = []
+
+        # Prepare selected device
+        self.prepare_device()
+        if not self.selected_device:
+            print("No audio input device selected")
+            return
+        if self.disconnected:
+            print("Audio source disconnected, please connect the audio source")
+            return False
+
+        # Prevent multiple recordings
+        if self.audio_source is not None:
+            return False
+
+        # Set up audio input and start recording
+        self.setup_audio_input()
+        return True
+
+    def stop(self):
+        """
+        Stop audio input recording
+
+        :return: True if stopped
+        """
+        result = False
+        if self.audio_source is not None:
+            # Disconnect the readyRead signal
+            self.audio_io_device.readyRead.disconnect(self.process_audio_input)
+            self.audio_source.stop()
+            self.audio_source = None
+            self.audio_io_device = None
+
+            # Save frames to file (if any)
+            if self.frames:
+                self.save_audio_file(self.path)
+                result = True
+            else:
+                print("No audio data recorded")
+        return result
+
+    def has_source(self) -> bool:
+        """
+        Check if audio source is available
+
+        :return: True if available
+        """
+        if self.audio_source is not None:
+            return True
+        return False
+
+    def has_frames(self) -> bool:
+        """
+        Check if audio frames are available
+
+        :return: True if available
+        """
+        if self.frames:
+            return True
+        return False
+
+    def get_frames(self) -> list:
+        """
+        Get recorded audio frames
+
+        :return: list of frames
+        """
+        return self.frames
+
+    def setup_audio_input(self):
+        """Set up audio input device and start recording"""
+        if not self.selected_device:
+            print("No audio input device selected")
+            return
+
+        # Define audio format
+        audio_format = QAudioFormat()
+        audio_format.setSampleRate(int(self.window.core.config.get('audio.input.rate', 44100)))
+        audio_format.setChannelCount(int(self.window.core.config.get('audio.input.channels', 1)))
+        audio_format.setSampleFormat(QAudioFormat.SampleFormat.Int16)
+
+        # Select default audio input device
+        audio_input_device = self.selected_device
+
+        # Check if the format is supported
+        if not audio_input_device.isFormatSupported(audio_format):
+            print("Requested format not supported, using nearest format.")
+            audio_format = audio_input_device.preferredFormat()
+
+        # Store the actual format being used
+        self.actual_audio_format = audio_format
+
+        # Create QAudioSource object with the device and format
+        try:
+            self.audio_source = QAudioSource(audio_input_device, audio_format)
+        except Exception as e:
+            self.disconnected = True
+            print(f"Failed to create audio source: {e}")
+
+        # Start audio input and obtain the QIODevice
+        try:
+            self.audio_io_device = self.audio_source.start()
+            if self.audio_io_device is None:
+                raise Exception("Unable to access audio input device")
+        except Exception as e:
+            print(f"Failed to start audio input: {e}")
+            self.disconnected = True
+            self.audio_source = None
+            self.audio_io_device = None
+            return
+
+        # Connect the readyRead signal to process incoming data
+        self.audio_io_device.readyRead.connect(self.process_audio_input)
+
+    def process_audio_input(self):
+        """Process incoming audio data"""
+        data = self.audio_io_device.readAll()
+        if data.isEmpty():
+            return
+
+        # Convert QByteArray to bytes
+        data_bytes = data.data()
+
+        # Append raw data to frames list for saving
+        self.frames.append(data_bytes)
+
+        # Determine the correct dtype and normalization factor
+        sample_format = self.actual_audio_format.sampleFormat()
+        dtype = self.get_dtype_from_sample_format(sample_format)
+        normalization_factor = self.get_normalization_factor(sample_format)
+
+        # Convert bytes to NumPy array of the appropriate type
+        samples = np.frombuffer(data_bytes, dtype=dtype)
+        if samples.size == 0:
+            return
+
+        # For unsigned formats, center the data
+        if sample_format == QAudioFormat.SampleFormat.UInt8:
+            samples = samples.astype(np.int16)
+            samples -= 128
+
+        # Compute RMS of the audio samples as float64 for precision
+        rms = np.sqrt(np.mean(samples.astype(np.float64) ** 2))
+
+        # Normalize RMS value based on the sample format
+        level = rms / normalization_factor
+
+        # Ensure level is within 0.0 to 1.0
+        level = min(max(level, 0.0), 1.0)
+
+        # Scale to 0-100
+        level_percent = level * 100
+
+        # Update the level bar widget
+        self.update_audio_level(level_percent)
+
+    def update_audio_level(self, level: int):
+        """
+        Update the audio level bar
+
+        :param level: audio level
+        """
+        if self.bar is not None:
+            self.bar.setLevel(level)
+
+    def reset_audio_level(self):
+        """Reset the audio level bar"""
+        if self.bar is not None:
+            self.bar.setLevel(0)
+
+    def save_audio_file(self, filename: str):
+        """
+        Save the recorded audio frames to a WAV file
+
+        :param filename: output file name
+        """
+        # Define the parameters for the WAV file
+        channels = self.actual_audio_format.channelCount()
+        sample_size = self.actual_audio_format.bytesPerSample()
+        frame_rate = self.actual_audio_format.sampleRate()
+
+        # Open the WAV file
+        wf = wave.open(filename, 'wb')
+        wf.setnchannels(channels)
+        wf.setsampwidth(sample_size)
+        wf.setframerate(frame_rate)
+
+        # Write frames to the file
+        wf.writeframes(b''.join(self.frames))
+        wf.close()
+
+    def get_dtype_from_sample_format(self, sample_format):
+        """
+        Get the NumPy dtype corresponding to the QAudioFormat sample format
+
+        :param sample_format: QAudioFormat.SampleFormat
+        """
+        if sample_format == QAudioFormat.SampleFormat.UInt8:
+            return np.uint8
+        elif sample_format == QAudioFormat.SampleFormat.Int16:
+            return np.int16
+        elif sample_format == QAudioFormat.SampleFormat.Int32:
+            return np.int32
+        elif sample_format == QAudioFormat.SampleFormat.Float:
+            return np.float32
+        else:
+            raise ValueError("Unsupported sample format")
+
+    def get_normalization_factor(self, sample_format):
+        """
+        Get the normalization factor for the QAudioFormat sample format
+
+        :param sample_format: QAudioFormat.SampleFormat
+        """
+        if sample_format == QAudioFormat.SampleFormat.UInt8:
+            return 255.0
+        elif sample_format == QAudioFormat.SampleFormat.Int16:
+            return 32768.0
+        elif sample_format == QAudioFormat.SampleFormat.Int32:
+            return float(2 ** 31)
+        elif sample_format == QAudioFormat.SampleFormat.Float:
+            return 1.0
+        else:
+            raise ValueError("Unsupported sample format")
+
+    def check_audio_input(self) -> bool:
+        """
+        Check if default audio input device is working
+
+        :return: True if working
+        """
+        import pyaudio
+        try:
+            rate = 44100
+            channels = 1
+            p = pyaudio.PyAudio()
+            stream = p.open(format=pyaudio.paInt16,
+                            channels=channels,
+                            rate=rate,
+                            input=True)
+            stream.stop_stream()
+            stream.close()
+            p.terminate()
+            return True
+        except Exception as e:
+            return False

pygpt_net/data/config/config.json

@@ -1,7 +1,7 @@
 {
   "__meta__": {
-    "version": "2.4.49",
-    "app.version": "2.4.49",
+    "version": "2.4.50",
+    "app.version": "2.4.50",
     "updated_at": "2025-01-16T00:00:00"
   },
   "access.audio.event.speech": false,

pygpt_net/data/config/models.json

@@ -1,7 +1,7 @@
 {
     "__meta__": {
-        "version": "2.4.49",
-        "app.version": "2.4.49",
+        "version": "2.4.50",
+        "app.version": "2.4.50",
         "updated_at": "2025-01-16T00:00:00"
     },
     "items": {

pygpt_net/data/config/modes.json

@@ -1,7 +1,7 @@
 {
     "__meta__": {
-        "version": "2.4.49",
-        "app.version": "2.4.49",
+        "version": "2.4.50",
+        "app.version": "2.4.50",
         "updated_at": "2025-01-16T00:00:00"
     },
     "items": {

pygpt_net/plugin/audio_input/simple.py

@@ -6,11 +6,9 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.08 00:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
-import pyaudio
-import wave
 import os
 
 from PySide6.QtCore import QTimer
@@ -32,9 +30,6 @@ class Simple:
         """
         self.plugin = plugin
         self.is_recording = False
-        self.frames = []
-        self.p = None
-        self.stream = None
         self.timer = None
 
     def toggle_recording(self):
@@ -61,54 +56,33 @@ class Simple:
 
     def start_recording(self):
         """Start recording"""
-        self.frames = []  # clear audio frames
-
-        def callback(in_data, frame_count, time_info, status):
-            self.frames.append(in_data)
-            if self.is_recording:
-                return (in_data, pyaudio.paContinue)
-            else:
-                return (in_data, pyaudio.paComplete)
-
         try:
-            self.is_recording = True
-            self.switch_btn_stop()
-
             # stop audio output if playing
             if self.plugin.window.controller.audio.is_playing():
                 self.plugin.window.controller.audio.stop_output()
 
+            # set audio volume bar
+            self.plugin.window.core.audio.capture.set_bar(
+                self.plugin.window.ui.plugin_addon['audio.input.btn'].bar
+            )
+
             # start timeout timer to prevent infinite recording
             if self.timer is None:
                 self.timer = QTimer()
                 self.timer.timeout.connect(self.stop_timeout)
                 self.timer.start(self.TIMEOUT_SECONDS * 1000)
 
-            # select audio input device
-            device_id = int(self.plugin.window.core.config.get('audio.input.device', 0))
-            rate = int(self.plugin.window.core.config.get('audio.input.rate', 44100))
-            channels = int(self.plugin.window.core.config.get('audio.input.channels', 1))
-            if not self.plugin.window.core.audio.is_device_compatible(device_id):
-                err = self.plugin.window.core.audio.get_last_error()
-                message = "Selected audio input device is not compatible. Please select another one. ERROR: " + str(err)
-                self.is_recording = False
-                self.plugin.window.core.debug.log(message)
-                self.plugin.window.ui.dialogs.alert(message)
-                self.switch_btn_start()  # switch button to start
-                return
-
-            self.p = pyaudio.PyAudio()
-            self.stream = self.p.open(format=pyaudio.paInt16,
-                                      channels=channels,
-                                      rate=rate,
-                                      input=True,
-                                      input_device_index=device_id,
-                                      frames_per_buffer=1024,
-                                      stream_callback=callback)
+            if not self.plugin.window.core.audio.capture.check_audio_input():
+                raise Exception("Audio input not working.")
+                # IMPORTANT!!!!
+                # Stop here if audio input not working!
+                # This prevents the app from freezing when audio input is not working!
 
+            self.is_recording = True
+            self.switch_btn_stop()
+            self.plugin.window.core.audio.capture.start()  # start recording if audio is OK
             self.plugin.window.update_status(trans('audio.speak.now'))
             self.plugin.window.dispatch(AppEvent(AppEvent.INPUT_VOICE_LISTEN_STARTED))  # app event
-            self.stream.start_stream()
         except Exception as e:
             self.is_recording = False
             self.plugin.window.core.debug.log(e)
@@ -127,6 +101,7 @@ class Simple:
 
         :param timeout: True if stopped due to timeout
         """
+        self.plugin.window.core.audio.capture.reset_audio_level()
         self.is_recording = False
         self.plugin.window.dispatch(AppEvent(AppEvent.INPUT_VOICE_LISTEN_STOPPED))  # app event
         if self.timer:
@@ -134,30 +109,22 @@ class Simple:
             self.timer = None
         self.switch_btn_start()  # switch button to start
         path = os.path.join(self.plugin.window.core.config.path, self.plugin.input_file)
+        self.plugin.window.core.audio.capture.set_path(path)
 
-        if self.stream is not None:
-            self.stream.stop_stream()
-            self.stream.close()
-            self.p.terminate()
-
+        if self.plugin.window.core.audio.capture.has_source():
+            self.plugin.window.core.audio.capture.stop()  # stop recording
             # abort if timeout
             if timeout:
                 self.plugin.window.update_status("Aborted.".format(self.TIMEOUT_SECONDS))
                 return
 
-            if self.frames:
-                if len(self.frames) < self.MIN_FRAMES:
+            if self.plugin.window.core.audio.capture.has_frames():
+                frames = self.plugin.window.core.audio.capture.get_frames()
+                if len(frames) < self.MIN_FRAMES:
                     self.plugin.window.update_status(trans("status.audio.too_short"))
                     self.plugin.window.dispatch(AppEvent(AppEvent.VOICE_CONTROL_STOPPED))  # app event
                     return
-                wf = wave.open(path, 'wb')
-                channels = int(self.plugin.window.core.config.get('audio.input.channels', 1))
-                rate = int(self.plugin.window.core.config.get('audio.input.rate', 44100))
-                wf.setnchannels(channels)
-                wf.setsampwidth(self.p.get_sample_size(pyaudio.paInt16))
-                wf.setframerate(rate)
-                wf.writeframes(b''.join(self.frames))
-                wf.close()
+
                 self.plugin.handle_thread(True)  # handle transcription in simple mode
         else:
             self.plugin.window.update_status("")

pygpt_net/ui/widget/audio/input_button.py

@@ -6,11 +6,12 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.11.20 21:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 from PySide6.QtCore import Qt
-from PySide6.QtWidgets import QLabel, QHBoxLayout, QWidget, QPushButton
+from PySide6.QtGui import QPainter
+from PySide6.QtWidgets import QLabel, QHBoxLayout, QWidget, QPushButton, QVBoxLayout
 
 from pygpt_net.core.events import Event, AppEvent
 from pygpt_net.utils import trans
@@ -31,14 +32,18 @@ class VoiceControlButton(QWidget):
         self.btn_toggle.setCursor(Qt.PointingHandCursor)
         self.btn_toggle.setMinimumWidth(200)
 
+        self.bar = LevelBar(self)
+        self.bar.setLevel(0)
+
         # status
         self.status = QLabel("")
         self.status.setStyleSheet("color: #999; font-size: 10px; font-weight: 400; margin: 0; padding: 0; border: 0;")
         self.status.setMaximumHeight(15)
 
-        self.layout = QHBoxLayout(self)
+        self.layout = QVBoxLayout(self)
         self.layout.addWidget(self.btn_toggle)
-        self.layout.addWidget(self.status)
+        # self.layout.addWidget(self.status)
+        self.layout.addWidget(self.bar)
 
         # self.layout.addWidget(self.stop)
         self.layout.setAlignment(Qt.AlignCenter)
@@ -82,14 +87,18 @@ class AudioInputButton(QWidget):
         self.btn_toggle.setCursor(Qt.PointingHandCursor)
         self.btn_toggle.setMinimumWidth(200)
 
+        self.bar = LevelBar(self)
+        self.bar.setLevel(0)
+
         # status
-        self.status = QLabel("")
-        self.status.setStyleSheet("color: #999; font-size: 10px; font-weight: 400; margin: 0; padding: 0; border: 0;")
-        self.status.setMaximumHeight(15)
+        #self.status = QLabel("xxx")
+        #self.status.setStyleSheet("color: #999; font-size: 10px; font-weight: 400; margin: 0; padding: 0; border: 0;")
+        #self.status.setMaximumHeight(15)
 
-        self.layout = QHBoxLayout(self)
+        self.layout = QVBoxLayout(self)
         self.layout.addWidget(self.btn_toggle)
-        self.layout.addWidget(self.status)
+        #self.layout.addWidget(self.status)
+        self.layout.addWidget(self.bar)
 
         # self.layout.addWidget(self.stop)
         self.layout.setAlignment(Qt.AlignCenter)
@@ -116,3 +125,46 @@ class AudioInputButton(QWidget):
         """Toggle recording"""
         event = Event(Event.AUDIO_INPUT_RECORD_TOGGLE)
         self.window.dispatch(event)
+
+
+class LevelBar(QWidget):
+    def __init__(self, parent=None):
+        super().__init__(parent)
+        self._level = 0.0  # level from 0.0 to 100.0
+        self.setFixedSize(200, 5)  # bar size
+
+    def setLevel(self, level):
+        """
+        Set volume level
+
+        :param level: level
+        """
+        self._level = level
+        self.update()
+
+    def paintEvent(self, event):
+        """
+        Paint event
+
+        :param event: event
+        """
+        painter = QPainter(self)
+        painter.fillRect(self.rect(), Qt.transparent)
+        level_width = (self._level / 100.0) * self.width()
+        painter.setBrush(Qt.green)
+        painter.setPen(Qt.NoPen)
+        painter.drawRect(0, 0, level_width, self.height())
+
+    """
+        # --- bar from center ---
+        def paintEvent(self, event):
+        painter = QPainter(self)
+        painter.fillRect(self.rect(), Qt.transparent)
+        level_width = (self._level / 100.0) * self.width()
+        half_level_width = level_width / 2
+        center_x = self.width() / 2
+        rect_x = center_x - half_level_width
+        painter.setBrush(Qt.green)
+        painter.setPen(Qt.NoPen)
+        painter.drawRect(rect_x, 0, level_width, self.height())
+    """

pygpt_net/ui/widget/dialog/snap.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.02.26 22:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 from PySide6.QtWidgets import QDialog, QLabel, QVBoxLayout, QPushButton
@@ -55,7 +55,7 @@ class SnapDialogAudioInput(QDialog):
         self.window = window
         self.setParent(window)
         self.setWindowTitle("Snap is detected")
-        self.cmd = CmdLabel(self.window, "sudo snap connect pygpt:audio-record :audio-record")
+        self.cmd = CmdLabel(self.window, "sudo snap connect pygpt:alsa && sudo snap connect pygpt:audio-record :audio-record")
 
         self.btn = QPushButton("OK")
         self.btn.clicked.connect(self.accept)

pygpt_net/ui/widget/dialog/update.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.02.17 20:00:00                  #
+# Updated Date: 2025.01.16 17:00:00                  #
 # ================================================== #
 
 import os
@@ -177,7 +177,8 @@ class UpdateDialog(BaseDialog):
                 if self.window.core.platforms.is_windows():
                     self.download_link = download_windows
                     self.download_file.setText("{} .msi ({})".format(trans("action.download"), version))
-                    self.download_file.setVisible(True)
+                    self.download_file.setVisible(False)  # Windows Store: disabled
+                    self.info_upgrade.setVisible(False)  # Windows Store: disabled
                 elif self.window.core.platforms.is_linux():
                     self.download_link = download_linux
                     self.download_file.setText("{} .tar.gz ({})".format(trans("action.download"), version))

{pygpt_net-2.4.49.dist-info → pygpt_net-2.4.50.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pygpt-net
-Version: 2.4.49
+Version: 2.4.50
 Summary: Desktop AI Assistant powered by models: OpenAI o1, GPT-4o, GPT-4, GPT-4 Vision, GPT-3.5, DALL-E 3, Llama 3, Mistral, Gemini, Claude, Bielik, and other models supported by Langchain, Llama Index, and Ollama. Features include chatbot, text completion, image generation, vision analysis, speech-to-text, internet access, file handling, command execution and more.
 Home-page: https://pygpt.net
 License: MIT
@@ -93,7 +93,7 @@ Description-Content-Type: text/markdown
 
 [![pygpt](https://snapcraft.io/pygpt/badge.svg)](https://snapcraft.io/pygpt)
 
-Release: **2.4.49** | build: **2025.01.16** | Python: **>=3.10, <3.13**
+Release: **2.4.50** | build: **2025.01.16** | Python: **>=3.10, <3.13**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -209,6 +209,7 @@ sudo snap connect pygpt:camera
 
 ```commandline
 sudo snap connect pygpt:audio-record :audio-record
+sudo snap connect pygpt:alsa
 ```
 
 **Connecting IPython in Docker in Snap version**:
@@ -4043,6 +4044,11 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**2.4.50 (2025-01-16)**
+
+- Refactored audio input core.
+- Added audio input volume progress bar.
+
 **2.4.49 (2025-01-16)**
 
 - Fix: stream render in Assistants mode.

{pygpt_net-2.4.49.dist-info → pygpt_net-2.4.50.dist-info}/RECORD

@@ -1,16 +1,16 @@
-CHANGELOG.md,sha256=gFRfBiL4PYqprFVvaUlx9AqT5AVpmhVjPK-YRLxle40,80939
-README.md,sha256=qkwiNaUhyZKE-g0wWxYUyd946edChMkH9Y-mPDOajG4,164846
+CHANGELOG.md,sha256=adPwRkkYgkZHuwQn1IB8ImnyuwtpSXTJoKvdA3zwEzI,81036
+README.md,sha256=WheYr0os5j1AVG5X4ifEyjK5swLluh01k7PCv8-wj5k,164973
 icon.png,sha256=CzcINJaU23a9hNjsDlDNbyuiEvKZ4Wg6DQVYF6SpuRg,13970
-pygpt_net/CHANGELOG.txt,sha256=-X0u1bg5Oq4rebB68yD00Movnr0rEPiC8aItUVHpn68,79456
+pygpt_net/CHANGELOG.txt,sha256=B1Gu0sgfveaUUwyPeqflV-uSmsdJbE39JSrukL92QM0,79550
 pygpt_net/LICENSE,sha256=dz9sfFgYahvu2NZbx4C1xCsVn9GVer2wXcMkFRBvqzY,1146
-pygpt_net/__init__.py,sha256=izcO_wLOAUU_jEhc6pCud7V2w6ywEptBfnZqqSstZnU,1307
+pygpt_net/__init__.py,sha256=u1pfEPJl3_fBwyjhEFbmNcNZv1jJ250_17nt8EK9XjY,1307
 pygpt_net/app.py,sha256=i02M96uLngAs_XZCS1Mi84vb3Okx8ZZewbTdhCqFolM,16029
 pygpt_net/config.py,sha256=Qc1FOBtTf3O6A6-6KoqUGtoJ0u8hXQeowvCVbZFwtik,16405
 pygpt_net/container.py,sha256=BemiVZPpPNIzfB-ZvnZeeBPFu-AcX2c30OqYFylEjJc,4023
 pygpt_net/controller/__init__.py,sha256=wtlkw4viFVuf2sP0iMSkK0jI1QMa3kcPfvQaqnC-1io,5917
 pygpt_net/controller/access/__init__.py,sha256=5DzR7zVmFsOICo9I5mEQcIOgsk2WCNi1amUWxExwUiY,2639
 pygpt_net/controller/access/control.py,sha256=nMGWzg60jNJMVAHIrism0_APzVMpbLAOcXG6mJuOSJ8,17332
-pygpt_net/controller/access/voice.py,sha256=Mt8waiGSc0p-aM8O_8OcGYjAxb0okgG0M1aHVbim9ok,15532
+pygpt_net/controller/access/voice.py,sha256=SJ6AdNOfvWWbegjLuNLrJTZ0K9uxcWx1Q47zVCXOsN8,15184
 pygpt_net/controller/agent/__init__.py,sha256=bArPuyZOJujcf4l1GKMMQ7Wx--xBoFHXz1A3TDjNjAk,1267
 pygpt_net/controller/agent/common.py,sha256=55CHhV-dsWeNe5QvdvNoyhEYVhQNrHt_Lv-VDTuiYRc,3871
 pygpt_net/controller/agent/experts.py,sha256=qllzrjVNfDoueBc0nsQLaWlOY4wpUKENp4l9cjWz0BM,5830
@@ -124,7 +124,8 @@ pygpt_net/core/assistants/store.py,sha256=4zz8_10_f6o8gdRekEPo5Ox0tLwuZO8tKyVsz-
 pygpt_net/core/attachments/__init__.py,sha256=bUqvfPqlpdXiGf3GvS1kTE45A0Q1Eo3kpUKypnRwDpk,12919
 pygpt_net/core/attachments/context.py,sha256=tQM3z_gLI99Ox47XZtVcUnOdfaPYKQwXhm1EJaNikvE,25057
 pygpt_net/core/attachments/worker.py,sha256=_aUCyi5-Mbz0IGfgY6QKBZ6MFz8aKRDfKasbBVXg7kU,1341
-pygpt_net/core/audio/__init__.py,sha256=78xr4fNQbj-0eWGwq3XuSdbIi7iLYn414C5cn_TWp18,4766
+pygpt_net/core/audio/__init__.py,sha256=uszH6pqMToDzL0WpPeUvVlyJ8RN4gFmQbsL4GFYMIdc,4521
+pygpt_net/core/audio/capture.py,sha256=BBxXM7KxxCxcvN7cW0b5dsSi8BphiLzEfkIt8PfN77Y,10408
 pygpt_net/core/audio/context.py,sha256=2XpXWhDC09iUvc0FRMq9BF2_rnQ60ZG4Js6LbO5MohY,1115
 pygpt_net/core/audio/whisper.py,sha256=WZ_fNQ06s1NBxyoYB-lTFqDO6ARcnq9MZFekRaTNxTo,993
 pygpt_net/core/bridge/__init__.py,sha256=ezS02_2wUrnV6eTF33wfob8rVWM5snfY92-PF_i15uQ,9568
@@ -246,9 +247,9 @@ pygpt_net/css_rc.py,sha256=i13kX7irhbYCWZ5yJbcMmnkFp_UfS4PYnvRFSPF7XXo,11349
 pygpt_net/data/audio/click_off.mp3,sha256=aNiRDP1pt-Jy7ija4YKCNFBwvGWbzU460F4pZWZDS90,65201
 pygpt_net/data/audio/click_on.mp3,sha256=qfdsSnthAEHVXzeyN4LlC0OvXuyW8p7stb7VXtlvZ1k,65201
 pygpt_net/data/audio/ok.mp3,sha256=LTiV32pEBkpUGBkKkcOdOFB7Eyt_QoP2Nv6c5AaXftk,32256
-pygpt_net/data/config/config.json,sha256=5HkaHlyhOoefxyM5HL1Oj_IhnC8PCFcaJ7dc6FPLOxc,19735
-pygpt_net/data/config/models.json,sha256=lrki8Hq-HafH_Nr-ijmoCtrFCmgll_hKdnlshsg5ag0,61940
-pygpt_net/data/config/modes.json,sha256=wxKhY9HJBjkj0lEtkwnod7aaz_iJmWY4eEyCVxY_5RU,1923
+pygpt_net/data/config/config.json,sha256=ezfhWuQCpy1HWm69Pc_7eVdtese2vwheLC3tb62h6Mo,19735
+pygpt_net/data/config/models.json,sha256=lhdi2Y9w3GxpRmpp07embuE4TVixvml9wbcoylMQA_8,61940
+pygpt_net/data/config/modes.json,sha256=KILDDam2UjJ-dCj8_PF9AnTlj4Xq4Ms9HYxOq2Krx-M,1923
 pygpt_net/data/config/presets/agent_openai.json,sha256=vMTR-soRBiEZrpJJHuFLWyx8a3Ez_BqtqjyXgxCAM_Q,733
 pygpt_net/data/config/presets/agent_openai_assistant.json,sha256=awJw9lNTGpKML6SJUShVn7lv8AXh0oic7wBeyoN7AYs,798
 pygpt_net/data/config/presets/agent_planner.json,sha256=a6Rv58Bnm2STNWB0Rw_dGhnsz6Lb3J8_GwsUVZaTIXc,742
@@ -1700,7 +1701,7 @@ pygpt_net/plugin/agent/__init__.py,sha256=GPbnpS9djcfzuPRxM2mu0hpUPRa51KtUR27Al6
 pygpt_net/plugin/agent/config.py,sha256=V4M0boutzxFVWTQxM8UA7HgKUR4v_Y-5dX_XfeLzzL8,9792
 pygpt_net/plugin/audio_input/__init__.py,sha256=vGwDtsPkwCEwiz2ePnzW48Tuhr0VHEc7kQua11VE7tI,15714
 pygpt_net/plugin/audio_input/config.py,sha256=x57IVxBapJp9rwos327T6U0jTFSPeRJ6BorqfYxJ4u0,9197
-pygpt_net/plugin/audio_input/simple.py,sha256=ea89IpCk_f-byqxdjDPCb3vvZH5nirO3ceP7-U54_Sc,6561
+pygpt_net/plugin/audio_input/simple.py,sha256=N5jL_hYp4ZvUBXqoiyx3Tt3b4bWKc9SbKOTtD00TNTE,5195
 pygpt_net/plugin/audio_input/worker.py,sha256=kG7r08ot1h0Jyw_UQ_sFN1rOKOkOC-ByLbCp-oZZBr4,11828
 pygpt_net/plugin/audio_output/__init__.py,sha256=wR_gBQgJ_arxHPSvjtT7naNwkNrCJc6KFR7ZUAqYcvc,7896
 pygpt_net/plugin/audio_output/config.py,sha256=IA2K-9fQMZSwYGyi30Uh5qAlYwuqwaHo3dtDJ13vQdo,1208
@@ -2073,7 +2074,7 @@ pygpt_net/ui/widget/anims/loader.py,sha256=PzxHraeABUyMIZlg4Rk_tbJnUPmiwxlhdcHaC
 pygpt_net/ui/widget/anims/toggles.py,sha256=_L2533IYyDkbnPCok9XBriIaKM5E9sHSznrwVWpKOOs,5755
 pygpt_net/ui/widget/audio/__init__.py,sha256=8HT4tQFqQogEEpGYTv2RplKBthlsFKcl5egnv4lzzEw,488
 pygpt_net/ui/widget/audio/input.py,sha256=t9VAhP15HkSOvNV2crI3Kg6AgrQDj-wSQiiYTMlvK60,1721
-pygpt_net/ui/widget/audio/input_button.py,sha256=e5nt91PcLZK0fNbzhvHeRYdpBzRNz-iusoPZziajs30,3695
+pygpt_net/ui/widget/audio/input_button.py,sha256=ykhBIRZ0g2w2f5YxOMkxtOndLDbdW4G8x3UbP1rVKyk,5185
 pygpt_net/ui/widget/audio/output.py,sha256=UxkiCnVT9DNFeByDGTFW_CK0LW8xSvhEK1zygtHvx4k,1586
 pygpt_net/ui/widget/calendar/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pygpt_net/ui/widget/calendar/select.py,sha256=vSEaQZmyeDhmyOfptWv6me_6IaYpQb5Jgc_mGDIe_4U,9051
@@ -2100,8 +2101,8 @@ pygpt_net/ui/widget/dialog/profile.py,sha256=vMYf-9c6HKAOqtSuw-HpBEUgmCSxEQuIrGl
 pygpt_net/ui/widget/dialog/rename.py,sha256=HcImKH_gUHcyB1k5llwStmrlXvcSpxgR2V6IuEdMuCU,2191
 pygpt_net/ui/widget/dialog/settings.py,sha256=fKzbme2tdxzTSiQMNnCEgyD3lwCzFjLi85ikWulisGw,1614
 pygpt_net/ui/widget/dialog/settings_plugin.py,sha256=Kf1ZK_RY9CAnfeuzPoQ4wgsFb2yQl7X-VKzsYETA55o,1696
-pygpt_net/ui/widget/dialog/snap.py,sha256=ESGmSSpExvf6WJ_EwiHJ9QK-t0NccfWeym5SSJNfi8I,2724
-pygpt_net/ui/widget/dialog/update.py,sha256=0z4motDKCchD8whFHGZJui9omM_dmpviqi3g5yjy6p0,6789
+pygpt_net/ui/widget/dialog/snap.py,sha256=UKiHOywK1tw0HelSgsUaKXMlageDdzOH_TJot3lUVUg,2756
+pygpt_net/ui/widget/dialog/update.py,sha256=aAmk-unSaGie3VXMaXmorza-p9Isrm06d0iSYnfcq3U,6900
 pygpt_net/ui/widget/dialog/url.py,sha256=7I17Pp9P2c3G1pODEY5dum_AF0nFnu2BMfbWTgEES-M,8765
 pygpt_net/ui/widget/dialog/workdir.py,sha256=D-C3YIt-wCoI-Eh7z--Z4R6P1UvtpkxeiaVcI-ycFck,1523
 pygpt_net/ui/widget/draw/__init__.py,sha256=oSYKtNEGNL0vDjn3wCgdnBAbxUqNGIEIf-75I2DIn7Q,488
@@ -2174,8 +2175,8 @@ pygpt_net/ui/widget/textarea/web.py,sha256=9FoL02QY6mOxtc4t4fe8X7fVDIdPn9Sb_fwsv
 pygpt_net/ui/widget/vision/__init__.py,sha256=8HT4tQFqQogEEpGYTv2RplKBthlsFKcl5egnv4lzzEw,488
 pygpt_net/ui/widget/vision/camera.py,sha256=T8b5cmK6uhf_WSSxzPt_Qod8JgMnst6q8sQqRvgQiSA,2584
 pygpt_net/utils.py,sha256=Gsh_mITVke3bb8o-Ke57l__xA5a9Wv4t7tlsnSQULj8,6655
-pygpt_net-2.4.49.dist-info/LICENSE,sha256=GLKQTnJOPK4dDIWfkAIM4GwOxKJXi5zcMGt7FjLR1xk,1126
-pygpt_net-2.4.49.dist-info/METADATA,sha256=j-CVH60IOvIiJj9FCjbFCeZBjm6stvp23QrJ7oZR85Q,169725
-pygpt_net-2.4.49.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-pygpt_net-2.4.49.dist-info/entry_points.txt,sha256=qvpII6UHIt8XfokmQWnCYQrTgty8FeJ9hJvOuUFCN-8,43
-pygpt_net-2.4.49.dist-info/RECORD,,
+pygpt_net-2.4.50.dist-info/LICENSE,sha256=GLKQTnJOPK4dDIWfkAIM4GwOxKJXi5zcMGt7FjLR1xk,1126
+pygpt_net-2.4.50.dist-info/METADATA,sha256=kttDYqtQSS0wi5lXkI3Y7APenTEcXuIVcRiuspWa_7Q,169852
+pygpt_net-2.4.50.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+pygpt_net-2.4.50.dist-info/entry_points.txt,sha256=qvpII6UHIt8XfokmQWnCYQrTgty8FeJ9hJvOuUFCN-8,43
+pygpt_net-2.4.50.dist-info/RECORD,,