pygpt-net 2.4.50__tar.gz → 2.4.52__tar.gz

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/CHANGELOG.md

@@ -1,5 +1,16 @@
 # CHANGELOG
 
+## 2.4.52 (2025-01-17)
+
+- Improved audio input button visibility toggle.
+- Fix: check for required arguments - issue #88.
+- UI Fixes.
+
+## 2.4.51 (2025-01-17)
+
+- Added a "Continuous recording" mode under Audio Input in the Notepad tab, allowing for recording long voice notes and real-time auto-transcription. (beta)
+- A new option has been added in Settings -> Audio -> Continuous recording auto-transcribe interval.
+
 ## 2.4.50 (2025-01-16)
 
 - Refactored audio input core.

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2024 Marcin Szczygliński
+Copyright (c) 2025 Marcin Szczygliński
 
 GitHub: https://github.com/szczyglis-dev/py-gpt
 

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pygpt-net
-Version: 2.4.50
+Version: 2.4.52
 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: **2.4.50** | build: **2025.01.16** | Python: **>=3.10, <3.13**
+Release: **2.4.52** | build: **2025.01.17** | Python: **>=3.10, <3.13**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -4044,6 +4044,17 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**2.4.52 (2025-01-17)**
+
+- Improved audio input button visibility toggle.
+- Fix: check for required arguments - issue #88.
+- UI Fixes.
+
+**2.4.51 (2025-01-17)**
+
+- Added a "Continuous recording" mode under Audio Input in the Notepad tab, allowing for recording long voice notes and real-time auto-transcription. (beta)
+- A new option has been added in Settings -> Audio -> Continuous recording auto-transcribe interval.
+
 **2.4.50 (2025-01-16)**
 
 - Refactored audio input core.
@@ -4074,67 +4085,6 @@ may consume additional tokens that are not displayed in the main window.
 - Introduced a new mode in "Chat with Files": "Retrieve Only", which allows for retrieving raw documents from the index.
 - Fixed a bug related to tool calls in the Gemini provider when using Chat with Files mode.
 
-**2.4.45 (2024-12-16)**
-
-- Enhanced web data loaders UI.
-
-**2.4.44 (2024-12-16)**
-
-- Enhanced web data loaders.
-- Web loaders have been added to attachments, allowing external web content to be attached to context via the "+Web" button in the Attachments tab.
-- Improved handling of attachments in groups and added an attachment icon when a group contains attachments.
-
-**2.4.43 (2024-12-15)**
-
-- Fix: Bug on attachment upload.
-- Added: Attachments uploaded in groups are now available for all contexts in the group (beta).
-
-**2.4.42 (2024-12-15)**
-
-- Added Mailer plugin, which allows sending and retrieving emails from the server, and reading them. It currently supports only SMTP.
-- Added 'web_request' command to the Web Search plugin, enabling GET/POST/PUT and other connections to any address and API endpoint. It also supports sending POST data, files, headers, cookies, and more.
-- Improved audio output.
-- Enhanced visibility of the Video menu.
-- Other fixes.
-
-**2.4.41 (2024-12-14)**
-
-- Improved switching between columns on a split screen.
-- Added visual identification of the active column.
-
-**2.4.40 (2024-12-13)**
-
-- Enhanced Split Screen mode, now promoted from beta to stable.
-- Python Code Interpreter tool added to the Tabs.
-- HTML/JS Canvas tool added to the Tabs.
-- Added attachment icon to the context list if context has attachments.
-- Improved audio playback.
-- Improved web search.
-- Added a thumbnail image to web search results.
-- Added a new commands to web search: "extract_images" and "extract_links".
-- Added the option "Use raw content (without summarization)" to the web search plugin, which provides a more detailed result to the main model.
-- Extended the default maximum result characters to 50,000 in the web search plugin.
-
-**2.4.39 (2024-12-09)**
-
-- Added "Split Screen" mode (accessible via the switch in the bottom-right corner of the screen), which allows you to work in two windows simultaneously. It is currently experimental (beta). Future updates will include Code Interpreter and Canvas running in tabs.
-
-- Fixed: Language switch.
-
-**2.4.38 (2024-12-08)**
-
-- Added the ability to select a style for chat display between: Blocks, ChatGPT-like, and ChatGPT-like Wide. New option in the menu: Config -> Theme -> Style...
-- Added configuration options for audio input in Settings -> Audio -> Audio Input Device, Channels, and Sampling rate.
-
-**2.4.37 (2024-11-30)**
-
-- The `Query only` mode in `Uploaded` tab has been renamed to `RAG`.
-- New options have been added under `Settings -> Files and Attachments`: 
-  - `Use history in RAG query`: When enabled, the content of the entire conversation will be used when preparing a query if the mode is set to RAG or Summary.
-  - `RAG limit`: This option is applicable only if 'Use history in RAG query' is enabled. It specifies the limit on how many recent entries in the conversation will be used when generating a query for RAG. A value of 0 indicates no limit.
-- Cache: dynamic parts of the system prompt (from plugins) have been moved to the very end of the prompt stack to enable the use of prompt cache mechanisms in OpenAI.
-
-
 # Credits and links
 
 **Official website:** <https://pygpt.net>

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/README.md

@@ -2,7 +2,7 @@
 
 [![pygpt](https://snapcraft.io/pygpt/badge.svg)](https://snapcraft.io/pygpt)
 
-Release: **2.4.50** | build: **2025.01.16** | Python: **>=3.10, <3.13**
+Release: **2.4.52** | build: **2025.01.17** | Python: **>=3.10, <3.13**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -3953,6 +3953,17 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**2.4.52 (2025-01-17)**
+
+- Improved audio input button visibility toggle.
+- Fix: check for required arguments - issue #88.
+- UI Fixes.
+
+**2.4.51 (2025-01-17)**
+
+- Added a "Continuous recording" mode under Audio Input in the Notepad tab, allowing for recording long voice notes and real-time auto-transcription. (beta)
+- A new option has been added in Settings -> Audio -> Continuous recording auto-transcribe interval.
+
 **2.4.50 (2025-01-16)**
 
 - Refactored audio input core.
@@ -3983,67 +3994,6 @@ may consume additional tokens that are not displayed in the main window.
 - Introduced a new mode in "Chat with Files": "Retrieve Only", which allows for retrieving raw documents from the index.
 - Fixed a bug related to tool calls in the Gemini provider when using Chat with Files mode.
 
-**2.4.45 (2024-12-16)**
-
-- Enhanced web data loaders UI.
-
-**2.4.44 (2024-12-16)**
-
-- Enhanced web data loaders.
-- Web loaders have been added to attachments, allowing external web content to be attached to context via the "+Web" button in the Attachments tab.
-- Improved handling of attachments in groups and added an attachment icon when a group contains attachments.
-
-**2.4.43 (2024-12-15)**
-
-- Fix: Bug on attachment upload.
-- Added: Attachments uploaded in groups are now available for all contexts in the group (beta).
-
-**2.4.42 (2024-12-15)**
-
-- Added Mailer plugin, which allows sending and retrieving emails from the server, and reading them. It currently supports only SMTP.
-- Added 'web_request' command to the Web Search plugin, enabling GET/POST/PUT and other connections to any address and API endpoint. It also supports sending POST data, files, headers, cookies, and more.
-- Improved audio output.
-- Enhanced visibility of the Video menu.
-- Other fixes.
-
-**2.4.41 (2024-12-14)**
-
-- Improved switching between columns on a split screen.
-- Added visual identification of the active column.
-
-**2.4.40 (2024-12-13)**
-
-- Enhanced Split Screen mode, now promoted from beta to stable.
-- Python Code Interpreter tool added to the Tabs.
-- HTML/JS Canvas tool added to the Tabs.
-- Added attachment icon to the context list if context has attachments.
-- Improved audio playback.
-- Improved web search.
-- Added a thumbnail image to web search results.
-- Added a new commands to web search: "extract_images" and "extract_links".
-- Added the option "Use raw content (without summarization)" to the web search plugin, which provides a more detailed result to the main model.
-- Extended the default maximum result characters to 50,000 in the web search plugin.
-
-**2.4.39 (2024-12-09)**
-
-- Added "Split Screen" mode (accessible via the switch in the bottom-right corner of the screen), which allows you to work in two windows simultaneously. It is currently experimental (beta). Future updates will include Code Interpreter and Canvas running in tabs.
-
-- Fixed: Language switch.
-
-**2.4.38 (2024-12-08)**
-
-- Added the ability to select a style for chat display between: Blocks, ChatGPT-like, and ChatGPT-like Wide. New option in the menu: Config -> Theme -> Style...
-- Added configuration options for audio input in Settings -> Audio -> Audio Input Device, Channels, and Sampling rate.
-
-**2.4.37 (2024-11-30)**
-
-- The `Query only` mode in `Uploaded` tab has been renamed to `RAG`.
-- New options have been added under `Settings -> Files and Attachments`: 
-  - `Use history in RAG query`: When enabled, the content of the entire conversation will be used when preparing a query if the mode is set to RAG or Summary.
-  - `RAG limit`: This option is applicable only if 'Use history in RAG query' is enabled. It specifies the limit on how many recent entries in the conversation will be used when generating a query for RAG. A value of 0 indicates no limit.
-- Cache: dynamic parts of the system prompt (from plugins) have been moved to the very end of the prompt stack to enable the use of prompt cache mechanisms in OpenAI.
-
-
 # Credits and links
 
 **Official website:** <https://pygpt.net>

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pygpt-net"
-version = "2.4.50"
+version = "2.4.52"
 description = "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."
 authors = ["Marcin Szczyglinski <info@pygpt.net>"]
 license = "MIT"

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/CHANGELOG.txt

@@ -1,3 +1,14 @@
+2.4.52 (2025-01-17)
+
+- Improved audio input button visibility toggle.
+- Fix: check for required arguments - issue #88.
+- UI Fixes.
+
+2.4.51 (2025-01-17)
+
+- Added a "Continuous recording" mode under Audio Input in the Notepad tab, allowing for recording long voice notes and real-time auto-transcription. (beta)
+- A new option has been added in Settings -> Audio -> Continuous recording auto-transcribe interval.
+
 2.4.50 (2025-01-16)
 
 - Refactored audio input core.

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/__init__.py

@@ -6,15 +6,15 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.01.16 17:00:00                  #
+# Updated Date: 2025.01.17 13:00:00                  #
 # ================================================== #
 
 __author__ = "Marcin Szczygliński"
 __copyright__ = "Copyright 2025, Marcin Szczygliński"
 __credits__ = ["Marcin Szczygliński"]
 __license__ = "MIT"
-__version__ = "2.4.50"
-__build__ = "2025.01.16"
+__version__ = "2.4.52"
+__build__ = "2025.01.17"
 __maintainer__ = "Marcin Szczygliński"
 __github__ = "https://github.com/szczyglis-dev/py-gpt"
 __report__ = "https://github.com/szczyglis-dev/py-gpt/issues"

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/controller/audio/__init__.py

@@ -6,12 +6,13 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.14 18:00:00                  #
+# Updated Date: 2025.01.17 13:00:00                  #
 # ================================================== #
 
 import os
 from typing import Optional
 
+from pygpt_net.core.tabs.tab import Tab
 from pygpt_net.core.events import Event, BaseEvent
 from pygpt_net.item.ctx import CtxItem
 from pygpt_net.utils import trans
@@ -25,10 +26,17 @@ class Audio:
         :param window: Window instance
         """
         self.window = window
+        self.input_allowed_tabs = [
+            Tab.TAB_NOTEPAD,
+            Tab.TAB_CHAT,
+            Tab.TAB_TOOL_CALENDAR,
+        ]
 
     def setup(self):
         """Setup controller"""
         self.update()
+        if self.window.core.config.get("audio.input.continuous", False):
+            self.window.ui.plugin_addon['audio.input.btn'].continuous.setChecked(True)
 
     def toggle_input(
             self,
@@ -54,6 +62,31 @@ class Audio:
         else:
             self.enable_output()
 
+    def toggle_continuous(self, state: bool):
+        """
+        Toggle continuous audio input
+
+        :param state: True to enable, False to disable
+        """
+        if state:
+            self.window.core.config.set("audio.input.continuous", True)
+        else:
+            self.window.core.config.set("audio.input.continuous", False)
+        self.window.core.config.save()
+
+    def on_tab_changed(self, tab: Tab):
+        """
+        On tab changed event
+
+        :param tab: Tab instance (current tab)
+        """
+        # input button visibility
+        if self.is_input_enabled():
+            if tab.type in self.input_allowed_tabs:
+                self.handle_audio_input(True)  # show btn
+            else:
+                self.handle_audio_input(False) # hide btn
+
     def enable_output(self):
         """Enable audio output"""
         self.toggle_output_icon(True)
@@ -347,3 +380,55 @@ class Audio:
         except Exception as e:
             pass
         return False
+
+    def handle_audio_input(
+            self,
+            is_enabled: bool
+    ):
+        """
+        Handle audio input UI
+
+        :param is_enabled: enable/disable audio input
+        """
+        # get advanced audio input option
+        is_advanced = False
+        data = {
+            'name': 'audio.input.advanced',
+            'value': is_advanced,
+        }
+        event = Event(Event.PLUGIN_OPTION_GET, data)
+        self.window.dispatch(event)
+        if 'value' in event.data:
+            is_advanced = event.data['value']
+        if is_enabled:
+            # show/hide extra options
+            tab = self.window.controller.ui.tabs.get_current_tab()
+            if tab.type == Tab.TAB_NOTEPAD:
+                self.window.ui.plugin_addon['audio.input.btn'].notepad_footer.setVisible(True)
+            else:
+                self.window.ui.plugin_addon['audio.input.btn'].notepad_footer.setVisible(False)
+            if is_advanced:
+                self.window.ui.plugin_addon['audio.input.btn'].setVisible(False)
+                self.window.ui.plugin_addon['audio.input'].setVisible(True)
+            else:
+                self.window.ui.plugin_addon['audio.input.btn'].setVisible(True)  # simple recording
+                self.window.ui.plugin_addon['audio.input'].setVisible(False)  # advanced recording
+            self.toggle_input_icon(True)
+        else:
+            self.window.ui.plugin_addon['audio.input.btn'].setVisible(False)  # simple recording
+            self.window.ui.plugin_addon['audio.input'].setVisible(False)  # advanced recording
+            self.toggle_input_icon(False)
+
+    def handle_audio_output(self, is_enabled: bool):
+        """
+        Handle audio output UI
+
+        :param is_enabled: enable/disable audio output
+        """
+        if is_enabled:
+            self.toggle_output_icon(True)
+            # self.window.ui.plugin_addon['audio.output'].setVisible(True)
+        else:
+            self.window.ui.plugin_addon['audio.output'].setVisible(False)
+            self.toggle_output_icon(False)
+

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/controller/lang/custom.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.09 00:00:00                  #
+# Updated Date: 2025.01.17 02:00:00                  #
 # ================================================== #
 
 from PySide6.QtCore import Qt
@@ -46,6 +46,7 @@ class Custom:
 
         # checkboxes
         self.window.ui.plugin_addon['audio.input'].btn_toggle.setText(trans('audio.speak.btn'))
+        self.window.ui.plugin_addon['audio.input.btn'].continuous.setText(trans('audio.speak.btn.continuous'))
         self.window.ui.config['assistant']['tool.file_search'].box.setText(trans('assistant.tool.file_search'))
         self.window.ui.config['assistant']['tool.code_interpreter'].box.setText(
             trans('assistant.tool.code_interpreter')

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/controller/plugins/__init__.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.14 08:00:00                  #
+# Updated Date: 2025.01.17 13:00:00                  #
 # ================================================== #
 
 from typing import List, Dict, Any
@@ -280,41 +280,16 @@ class Plugins:
         """Handle plugin type"""
         for type in self.window.core.plugins.allowed_types:
 
-            # get advanced audio input option
-            is_advanced = False
-            data = {
-                'name': 'audio.input.advanced',
-                'value': is_advanced,
-            }
-            event = Event(Event.PLUGIN_OPTION_GET, data)
-            self.window.dispatch(event)
-            if 'value' in event.data:
-                is_advanced = event.data['value']
+            enabled = self.is_type_enabled(type)
 
             if type == 'audio.input':
-                if self.is_type_enabled(type):
-                    if is_advanced:
-                        self.window.ui.plugin_addon['audio.input.btn'].setVisible(False)
-                        self.window.ui.plugin_addon['audio.input'].setVisible(True)
-                    else:
-                        self.window.ui.plugin_addon['audio.input.btn'].setVisible(True)  # simple recording
-                        self.window.ui.plugin_addon['audio.input'].setVisible(False)  # advanced recording
-                    self.window.controller.audio.toggle_input_icon(True)
-                else:
-                    self.window.ui.plugin_addon['audio.input.btn'].setVisible(False)  # simple recording
-                    self.window.ui.plugin_addon['audio.input'].setVisible(False)  # advanced recording
-                    self.window.controller.audio.toggle_input_icon(False)
+                self.window.controller.audio.handle_audio_input(enabled)
 
             elif type == 'audio.output':
-                if self.is_type_enabled(type):
-                    self.window.controller.audio.toggle_output_icon(True)
-                    # self.window.ui.plugin_addon['audio.output'].setVisible(True)
-                else:
-                    self.window.ui.plugin_addon['audio.output'].setVisible(False)
-                    self.window.controller.audio.toggle_output_icon(False)
+                self.window.controller.audio.handle_audio_output(enabled)
 
             elif type == 'schedule':
-                if self.is_type_enabled(type):
+                if enabled:
                     self.window.ui.plugin_addon['schedule'].setVisible(True)
                     # get tasks count by throwing "get option" event
                     num = 0

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/controller/ui/tabs.py

@@ -6,13 +6,11 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.14 07:00:00                  #
+# Updated Date: 2025.01.17 13:00:00                  #
 # ================================================== #
 
 from typing import Any, Optional
 
-from PySide6.QtCore import QTimer
-
 from pygpt_net.core.events import AppEvent, RenderEvent
 from pygpt_net.core.tabs.tab import Tab
 from pygpt_net.item.ctx import CtxMeta
@@ -182,9 +180,18 @@ class Tabs:
         if prev_tab != idx or prev_column != column_idx:
             self.window.dispatch(AppEvent(AppEvent.TAB_SELECTED))  # app event
 
+        self.on_changed()
+
         self.window.controller.ui.update()
         self.update_current()
 
+    def on_changed(self):
+        """On Tab or column changed event (any)"""
+        tab = self.get_current_tab()
+        if tab is None:
+            return
+        self.window.controller.audio.on_tab_changed(tab)
+
     def get_current_idx(self, column_idx: int = 0) -> int:
         """
         Get current tab index
@@ -291,6 +298,7 @@ class Tabs:
         self.current = idx
         self.column_idx = column_idx
         self.on_column_changed()
+        self.on_changed()
         self.update_current()
 
     def on_column_focus(self, idx: int):
@@ -301,6 +309,7 @@ class Tabs:
         """
         self.column_idx = idx
         self.on_column_changed()
+        self.on_changed()
         self.update_current()
 
     def on_tab_dbl_clicked(
@@ -332,6 +341,7 @@ class Tabs:
         if self.locked:
             return
         self.window.core.tabs.remove_tab_by_idx(idx, column_idx)
+        self.on_changed()
         self.update_current()
 
     def on_tab_moved(
@@ -387,6 +397,7 @@ class Tabs:
             return
         column_idx = self.tmp_column_idx
         self.window.core.tabs.remove_all_by_type(type, column_idx)
+        self.on_changed()
         self.update_current()
 
     def next_tab(self):

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/core/audio/capture.py

@@ -6,13 +6,16 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.01.16 17:00:00                  #
+# Updated Date: 2025.01.17 02:00:00                  #
 # ================================================== #
 
+import time
+
 import numpy as np
 import wave
 
 from PySide6.QtMultimedia import QAudioFormat, QMediaDevices, QAudioSource
+from PySide6.QtCore import QTimer
 
 class Capture:
     def __init__(self, window=None):
@@ -28,6 +31,9 @@ class Capture:
         self.actual_audio_format = None
         self.path = None
         self.disconnected = False
+        self.loop = False
+        self.stop_callback = None
+        self.start_time = 0
         self.devices = []
         self.selected_device = None
         self.bar = None
@@ -100,6 +106,7 @@ class Capture:
 
         # Set up audio input and start recording
         self.setup_audio_input()
+        self.start_time = time.time()
         return True
 
     def stop(self):
@@ -199,6 +206,7 @@ class Capture:
 
     def process_audio_input(self):
         """Process incoming audio data"""
+        # add seconds to stop timer
         data = self.audio_io_device.readAll()
         if data.isEmpty():
             return
@@ -239,6 +247,16 @@ class Capture:
         # Update the level bar widget
         self.update_audio_level(level_percent)
 
+        # Handle loop recording
+        if self.loop and self.stop_callback is not None:
+            stop_interval = int(self.window.core.config.get('audio.input.stop_interval', 10))
+            current_time = time.time()
+            time_elapsed = current_time - self.start_time
+            if time_elapsed >= stop_interval:
+                # stop recording here, save audio chunk to WAV file, run transcription, and start recording again
+                self.start_time = current_time
+                QTimer.singleShot(0, self.stop_callback)  # required QTimer to prevent crash!!!
+
     def update_audio_level(self, level: int):
         """
         Update the audio level bar

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/data/config/config.json

@@ -1,8 +1,8 @@
 {
   "__meta__": {
-    "version": "2.4.50",
-    "app.version": "2.4.50",
-    "updated_at": "2025-01-16T00:00:00"
+    "version": "2.4.52",
+    "app.version": "2.4.52",
+    "updated_at": "2025-01-17T00:00:00"
   },
   "access.audio.event.speech": false,
   "access.audio.event.speech.disabled": [],
@@ -74,8 +74,10 @@
   "attachments_send_clear": true,
   "attachments_capture_clear": true,
   "audio.input.channels": 1,
+  "audio.input.continuous": false,
   "audio.input.device": "0",
   "audio.input.rate": 44100,
+  "audio.input.stop_interval": 10,
   "audio.transcribe.convert_video": true,
   "context_threshold": 200,
   "cmd": false,

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/data/config/models.json

@@ -1,8 +1,8 @@
 {
     "__meta__": {
-        "version": "2.4.50",
-        "app.version": "2.4.50",
-        "updated_at": "2025-01-16T00:00:00"
+        "version": "2.4.52",
+        "app.version": "2.4.52",
+        "updated_at": "2025-01-17T00:00:00"
     },
     "items": {
         "claude-3-5-sonnet-20240620": {

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/data/config/modes.json

@@ -1,8 +1,8 @@
 {
     "__meta__": {
-        "version": "2.4.50",
-        "app.version": "2.4.50",
-        "updated_at": "2025-01-16T00:00:00"
+        "version": "2.4.52",
+        "app.version": "2.4.52",
+        "updated_at": "2025-01-17T00:00:00"
     },
     "items": {
         "chat": {

{pygpt_net-2.4.50 → pygpt_net-2.4.52}/src/pygpt_net/data/config/settings.json

@@ -1123,6 +1123,19 @@
         "step": 1,
         "advanced": false
     },
+    "audio.input.stop_interval": {
+        "section": "audio",
+        "type": "int",
+        "slider": true,
+        "label": "settings.audio.input.stop_interval",
+        "description": "settings.audio.input.stop_interval.desc",
+        "value": 10,
+        "min": 5,
+        "max": 120,
+        "multiplier": 1,
+        "step": 1,
+        "advanced": false
+    },
     "llama.idx.list": {
         "section": "llama-index",
         "type": "dict",