pygpt-net 2.5.90__py3-none-any.whl → 2.5.92__py3-none-any.whl

pygpt_net/CHANGELOG.txt

@@ -1,3 +1,12 @@
+2.5.92 (2025-08-08)
+
+- Added max files to store config option in Audio -> Cache.
+
+2.5.91 (2025-08-08)
+
+- Added GPT-5.
+- Added audio cache - #118.
+
 2.5.90 (2025-08-07)
 
 - Fix: Initialize context summary if a conversation starts with a tool call.

pygpt_net/__init__.py

@@ -6,15 +6,15 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.07 00:00:00                  #
+# Updated Date: 2025.08.08 00:00:00                  #
 # ================================================== #
 
 __author__ = "Marcin Szczygliński"
 __copyright__ = "Copyright 2025, Marcin Szczygliński"
 __credits__ = ["Marcin Szczygliński"]
 __license__ = "MIT"
-__version__ = "2.5.90"
-__build__ = "2025-08-07"
+__version__ = "2.5.92"
+__build__ = "2025-08-08"
 __maintainer__ = "Marcin Szczygliński"
 __github__ = "https://github.com/szczyglis-dev/py-gpt"
 __report__ = "https://github.com/szczyglis-dev/py-gpt/issues"

pygpt_net/controller/access/voice.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.07 03:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 from typing import Optional, List, Dict, Any
@@ -231,8 +231,7 @@ class Voice(QObject):
             self.switch_btn_stop()
 
             # stop audio output if playing
-            if self.window.controller.audio.is_playing():
-                self.window.controller.audio.stop_output()
+            self.window.controller.audio.stop_output()
 
             # set audio volume bar
             self.window.core.audio.capture.set_bar(

pygpt_net/controller/audio/audio.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.01.17 13:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 import os
@@ -291,7 +291,7 @@ class Audio:
 
         if use_cache:
             lang = self.window.core.config.get("lang")
-            cache_dir = os.path.join(self.window.core.config.get_user_path(), "cache", "audio", lang)
+            cache_dir = os.path.join(self.window.core.audio.get_cache_dir(), lang)
             if not os.path.exists(cache_dir):
                 os.makedirs(cache_dir, exist_ok=True)
             cache_file = os.path.join(str(cache_dir), event.name + ".wav")
@@ -318,7 +318,7 @@ class Audio:
             )
             return
 
-        cache_dir = os.path.join(self.window.core.config.get_user_path(), "cache", "audio")
+        cache_dir = self.window.core.audio.get_cache_dir()
         if os.path.exists(cache_dir):
             import shutil
             shutil.rmtree(cache_dir)
@@ -352,7 +352,10 @@ class Audio:
 
         :param text: text to play
         """
-        self.window.update_status(trans("status.audio.start"))
+        if text:
+            self.window.update_status(trans("status.audio.start"))
+        else:
+            self.window.update_status("")
         QApplication.processEvents()  # process events to update UI
 
     def on_play(self, event: str):

pygpt_net/controller/ctx/extra.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.07.14 18:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 from PySide6.QtWidgets import QApplication
@@ -220,12 +220,7 @@ class Extra:
                 self.window.controller.audio.read_text(item.output)
                 self.audio_play_id = item_id
             elif self.audio_play_id == item_id:
-                if not self.window.controller.audio.is_playing():
-                    self.window.controller.audio.read_text(item.output)
-                else:
-                    self.window.controller.audio.stop_output()
-                    self.window.controller.audio.on_stop()
-                    self.audio_play_id = None
+                self.window.controller.audio.read_text(item.output)
 
     def join_item(
             self,

pygpt_net/controller/kernel/kernel.py

@@ -52,6 +52,7 @@ class Kernel(QObject):
             KernelEvent.APPEND_DATA, 
             KernelEvent.INPUT_USER,
             KernelEvent.FORCE_CALL,
+            KernelEvent.STATUS,
         ]
 
     def init(self):

pygpt_net/core/audio/audio.py

@@ -6,9 +6,11 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.07 03:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
+import hashlib
+import os
 import re
 from typing import Union, Optional, Tuple, List
 
@@ -21,6 +23,9 @@ from .whisper import Whisper
 
 
 class Audio:
+
+    CACHE_FORMAT = "mp3"  # default cache format
+
     def __init__(self, window=None):
         """
         Audio input/output core
@@ -173,3 +178,80 @@ class Audio:
         :return: Error
         """
         return self.last_error
+
+    def prepare_cache_path(self, content: str) -> Tuple[Union[str, None], bool]:
+        """
+        Prepare unique cache file name for given content
+
+        :param content: text content to generate cache file name
+        :return: cache file path or None if content is empty
+        """
+        exists = False
+        if not content:
+            return None, exists
+        sha1sum = hashlib.sha1(content.encode('utf-8')).hexdigest()
+        filename = f"{sha1sum}." + self.CACHE_FORMAT
+        tmp_dir = self.get_cache_dir()
+        path = os.path.join(tmp_dir, filename)
+        if os.path.exists(path):
+            exists = True
+        return str(path), exists
+
+    def get_cache_dir(self) -> str:
+        """
+        Get cache directory for audio files
+
+        :return: audio cache directory path
+        """
+        dir = self.window.core.config.get_user_dir("tmp")
+        if not os.path.exists(dir):
+            os.makedirs(dir, exist_ok=True)
+        tmp_dir = os.path.join(dir, "audio_cache")
+        if not os.path.exists(tmp_dir):
+            os.makedirs(tmp_dir, exist_ok=True)
+        return tmp_dir
+
+    def delete_old_cache(self, max_files: int = 10):
+        """
+        Delete old cache files, keeping only the most recent ones.
+
+        :param max_files: Maximum number of cache files to keep.
+        """
+        tmp_dir = self.get_cache_dir()
+        files = [os.path.join(tmp_dir, f) for f in os.listdir(tmp_dir) if f.endswith('.' + self.CACHE_FORMAT)]
+        files.sort(key=os.path.getmtime, reverse=True)
+        for file in files[max_files:]:
+            try:
+                os.remove(file)
+            except Exception as e:
+                print(f"Error deleting cache file {file}: {e}")
+
+    def mp3_to_wav(
+            self,
+            src_file: str,
+            dst_file: Optional[str] = None
+    ) -> Union[str, None]:
+        """
+        Convert MP3 file to WAV format
+
+        :param src_file: Path to the source MP3 file
+        :param dst_file: Optional path for the destination WAV file.
+        :return: Path to the converted WAV file or None if conversion fails.
+        """
+        from pydub import AudioSegment
+        try:
+            mp3_audio = AudioSegment.from_mp3(src_file)
+        except Exception as e:
+            print(f"Error loading mp3 file: {e}")
+            print("Please install ffmpeg to handle mp3 files: https://ffmpeg.org/")
+            return
+        if dst_file is None:
+            dir = os.path.dirname(src_file)
+            filename = os.path.splitext(os.path.basename(src_file))[0] + ".wav"
+            dst_file = os.path.join(dir, filename)
+        try:
+            mp3_audio.export(dst_file, format="wav")
+            return str(dst_file)
+        except Exception as e:
+            print(f"Error exporting wav file: {e}")
+            return

pygpt_net/core/audio/backend/native.py

@@ -6,18 +6,21 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.07 03:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
+import os
 import time
 from typing import List, Tuple
 
 from PySide6.QtCore import QTimer, QObject
+from pydub import AudioSegment
 
 
 class NativeBackend(QObject):
 
     MIN_FRAMES = 25  # minimum frames to start transcription
+    AUTO_CONVERT_TO_WAV = False  # automatically convert to WAV format
 
     def __init__(self, window=None):
         """
@@ -42,7 +45,10 @@ class NativeBackend(QObject):
         self.stop_callback = None
         self.player = None
         self.playback_timer = None
+        self.volume_timer = None
         self.audio_output = None
+        self.envelope = []
+        self.chunk_ms = 10
 
         # Get configuration values (use defaults if unavailable)
         if self.window is not None and hasattr(self.window, "core"):
@@ -457,8 +463,6 @@ class NativeBackend(QObject):
         :param signals: Signals to emit on playback
         :return: True if started
         """
-        import os
-        from pydub import AudioSegment
         from PySide6.QtMultimedia import QMediaPlayer, QAudioOutput, QMediaDevices
         from PySide6.QtCore import QUrl, QTimer
         if signals is not None:
@@ -476,42 +480,57 @@ class NativeBackend(QObject):
             selected_device = devices[num_device] if num_device < len(devices) else devices[0]
             self.audio_output.setDevice(selected_device)
 
-        self.player = QMediaPlayer()
-        self.player.setAudioOutput(self.audio_output)
-
-        if audio_file.lower().endswith('.mp3'):
-            try:
-                mp3_audio = AudioSegment.from_mp3(audio_file)
-            except Exception as e:
-                print(f"Error loading mp3 file: {e}")
-                return
-
-            base_dir = self.window.core.config.get_user_path()
-            base_name = os.path.splitext(os.path.basename(audio_file))[0]
-            wav_file = os.path.join(base_dir, "_" + base_name + ".wav")
-            try:
-                mp3_audio.export(wav_file, format="wav")
-            except Exception as e:
-                print(f"Error exporting wav file: {e}")
-                return
-
-            self.player.setSource(QUrl.fromLocalFile(wav_file))
-        else:
-            self.player.setSource(QUrl.fromLocalFile(audio_file))
-
-        self.player.play()
-        self.playback_timer = QTimer()
-        self.playback_timer.setInterval(100)
+        if self.AUTO_CONVERT_TO_WAV:
+            if audio_file.lower().endswith('.mp3'):
+                tmp_dir = self.window.core.audio.get_cache_dir()
+                base_name = os.path.splitext(os.path.basename(audio_file))[0]
+                dst_file = os.path.join(tmp_dir, "_" + base_name + ".wav")
+                wav_file = self.window.core.audio.mp3_to_wav(audio_file, dst_file)
+                if wav_file:
+                    audio_file = wav_file
 
         def check_stop():
             if stopped():
                 self.player.stop()
-                self.playback_timer.stop()
+                self.stop_timers()
+                signals.volume_changed.emit(0)
+            else:
+                if self.player:
+                    if self.player.playbackState() == QMediaPlayer.StoppedState:
+                        self.player.stop()
+                        self.stop_timers()
+                        signals.volume_changed.emit(0)
 
+        self.envelope = self.calculate_envelope(audio_file, self.chunk_ms)
+        self.player = QMediaPlayer()
+        self.player.setAudioOutput(self.audio_output)
+        self.player.setSource(QUrl.fromLocalFile(audio_file))
+        self.player.play()
+
+        self.playback_timer = QTimer()
+        self.playback_timer.setInterval(100)
         self.playback_timer.timeout.connect(check_stop)
+        self.volume_timer = QTimer(self)
+        self.volume_timer.setInterval(10)  # every 100 ms
+        self.volume_timer.timeout.connect(
+            lambda: self.update_volume(signals)
+        )
+
         self.playback_timer.start()
+        self.volume_timer.start()
         signals.volume_changed.emit(0)
 
+    def stop_timers(self):
+        """
+        Stop playback timers.
+        """
+        if self.playback_timer is not None:
+            self.playback_timer.stop()
+            self.playback_timer = None
+        if self.volume_timer is not None:
+            self.volume_timer.stop()
+            self.volume_timer = None
+
     def play(
             self,
             audio_file: str,
@@ -543,6 +562,49 @@ class NativeBackend(QObject):
                 self.playback_timer.stop()
         return False
 
+    def calculate_envelope(
+            self,
+            audio_file: str,
+            chunk_ms: int = 100
+    ) -> list:
+        """
+        Calculate the volume envelope of an audio file.
+
+        :param audio_file: Path to the audio file
+        :param chunk_ms: Size of each chunk in milliseconds
+        """
+        import numpy as np
+        audio = AudioSegment.from_file(audio_file)
+        max_amplitude = 32767
+        envelope = []
+
+        for ms in range(0, len(audio), chunk_ms):
+            chunk = audio[ms:ms + chunk_ms]
+            rms = chunk.rms
+            if rms > 0:
+                db = 20 * np.log10(rms / max_amplitude)
+            else:
+                db = -60
+            db = max(-60, min(0, db))
+            volume = ((db + 60) / 60) * 100
+            envelope.append(volume)
+
+        return envelope
+
+    def update_volume(self, signals=None):
+        """
+        Update the volume based on the current position in the audio file.
+
+        :param signals: Signals object to emit volume changed event.
+        """
+        pos = self.player.position()
+        index = int(pos / self.chunk_ms)
+        if index < len(self.envelope):
+            volume = self.envelope[index]
+        else:
+            volume = 0
+        signals.volume_changed.emit(volume)
+
     def get_input_devices(self) -> List[Tuple[int, str]]:
         """
         Get input devices

pygpt_net/data/config/config.json

@@ -1,8 +1,8 @@
 {
   "__meta__": {
-    "version": "2.5.90",
-    "app.version": "2.5.90",
-    "updated_at": "2025-08-07T00:00:00"
+    "version": "2.5.92",
+    "app.version": "2.5.92",
+    "updated_at": "2025-08-08T00:00:00"
   },
   "access.audio.event.speech": false,
   "access.audio.event.speech.disabled": [],
@@ -94,6 +94,8 @@
   "attachments_auto_index": true,
   "attachments_send_clear": true,
   "attachments_capture_clear": true,
+  "audio.cache.enabled": true,
+  "audio.cache.max_files": 1000,
   "audio.input.backend": "native",
   "audio.input.channels": 1,
   "audio.input.continuous": false,

pygpt_net/data/config/models.json

@@ -1,8 +1,8 @@
 {
     "__meta__": {
-        "version": "2.5.90",
-        "app.version": "2.5.90",
-        "updated_at": "2025-08-07T23:07:35"
+        "version": "2.5.92",
+        "app.version": "2.5.92",
+        "updated_at": "2025-08-08T23:07:35"
     },
     "items": {
         "SpeakLeash/bielik-11b-v2.3-instruct:Q4_K_M": {
@@ -2028,6 +2028,171 @@
             "provider": "openai",
             "tool_calls": true
         },
+        "gpt-5": {
+            "id": "gpt-5",
+            "name": "gpt-5",
+            "mode": [
+                "chat",
+                "assistant",
+                "llama_index",
+                "vision",
+                "agent",
+                "agent_llama",
+                "expert",
+                "agent_openai"
+            ],
+            "llama_index": {
+                "args": [
+                    {
+                        "name": "model",
+                        "value": "gpt-5",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "ctx": 400000,
+            "tokens": 128000,
+            "default": true,
+            "input": [
+                "text",
+                "image"
+            ],
+            "output": [
+                "text"
+            ],
+            "extra": {},
+            "imported": false,
+            "provider": "openai",
+            "tool_calls": true
+        },
+        "gpt-5-mini": {
+            "id": "gpt-5-mini",
+            "name": "gpt-5-mini",
+            "mode": [
+                "chat",
+                "assistant",
+                "llama_index",
+                "vision",
+                "agent",
+                "agent_llama",
+                "expert",
+                "agent_openai"
+            ],
+            "llama_index": {
+                "args": [
+                    {
+                        "name": "model",
+                        "value": "gpt-5-mini",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "ctx": 400000,
+            "tokens": 128000,
+            "default": true,
+            "input": [
+                "text",
+                "image"
+            ],
+            "output": [
+                "text"
+            ],
+            "extra": {},
+            "imported": false,
+            "provider": "openai",
+            "tool_calls": true
+        },
+        "gpt-5-nano": {
+            "id": "gpt-5-nano",
+            "name": "gpt-5-nano",
+            "mode": [
+                "chat",
+                "assistant",
+                "llama_index",
+                "vision",
+                "agent",
+                "agent_llama",
+                "expert",
+                "agent_openai"
+            ],
+            "llama_index": {
+                "args": [
+                    {
+                        "name": "model",
+                        "value": "gpt-5-nano",
+                        "type": "str"
+                    }
+                ],
+                "env": [
+                    {
+                        "name": "OPENAI_API_KEY",
+                        "value": "{api_key}"
+                    },
+                    {
+                        "name": "OPENAI_API_BASE",
+                        "value": "{api_endpoint}"
+                    },
+                    {
+                        "name": "AZURE_OPENAI_ENDPOINT",
+                        "value": "{api_azure_endpoint}"
+                    },
+                    {
+                        "name": "OPENAI_API_VERSION",
+                        "value": "{api_azure_version}"
+                    }
+                ]
+            },
+            "ctx": 400000,
+            "tokens": 128000,
+            "default": true,
+            "input": [
+                "text",
+                "image"
+            ],
+            "output": [
+                "text"
+            ],
+            "extra": {},
+            "imported": false,
+            "provider": "openai",
+            "tool_calls": true
+        },
         "gpt-image-1": {
             "id": "gpt-image-1",
             "name": "gpt-image-1",

pygpt_net/data/config/settings.json

@@ -1373,7 +1373,7 @@
         "step": 1,
         "advanced": false,        
         "tab": "device"
-    },    
+    }, 
     "audio.input.stop_interval": {
         "section": "audio",
         "type": "int",
@@ -1414,6 +1414,28 @@
         "advanced": false,        
         "tab": "options"
     },
+    "audio.cache.enabled": {
+        "section": "audio",
+        "type": "bool",
+        "slider": true,
+        "label": "settings.audio.cache.enabled",
+        "description": "settings.audio.cache.enabled.desc",
+        "value": true,
+        "advanced": false,        
+        "tab": "cache"
+    },
+    "audio.cache.max_files": {
+        "section": "audio",
+        "type": "int",
+        "slider": false,
+        "label": "settings.audio.cache.max_files",
+        "description": "settings.audio.cache.max_files.desc",
+        "min": 0,
+        "multiplier": 1,
+        "value": 1000,
+        "advanced": false,        
+        "tab": "cache"
+    },
     "remote_tools.web_search": {
         "section": "remote_tools",
         "type": "bool",

pygpt_net/data/locale/locale.de.ini

@@ -1025,6 +1025,10 @@ settings.api_use_responses_llama = Verwenden Sie die Responses API im Chat mit D
 settings.api_use_responses_llama.desc = Verwende Responses API anstelle von ChatCompletions API im Chat-mit-Dateien-Modus (LlamaIndex). Nur OpenAI-Modelle.
 settings.app.env = Anwendungsumgebung (os.environ)
 settings.app.env.desc = Zusätzliche Umgebungsvariablen, die beim Start der Anwendung gesetzt werden sollen
+settings.audio.cache.enabled = Cache aktivieren
+settings.audio.cache.enabled.desc = Aktivieren Sie das Audio-Caching für die Spracherzeugung.
+settings.audio.cache.max_files = Maximale Anzahl zu speichernder Dateien
+settings.audio.cache.max_files.desc = Maximale Anzahl gecachter Audiodateien, die auf der Festplatte gespeichert werden
 settings.audio.input.backend = Backend für Audioeingabe
 settings.audio.input.backend.desc = Wählen Sie das Backend für die Audioeingabe.
 settings.audio.input.channels = Kanäle
@@ -1239,6 +1243,7 @@ settings.section.api_keys.openai = OpenAI
 settings.section.api_keys.perplexity = Perplexity
 settings.section.api_keys.xai = xAI
 settings.section.audio = Audio
+settings.section.audio.cache = Cache
 settings.section.audio.device = Geräte
 settings.section.audio.options = Optionen
 settings.section.ctx = Kontext

pygpt_net/data/locale/locale.en.ini

@@ -1031,6 +1031,10 @@ settings.api_use_responses_llama = Use Responses API in Chat with Files mode (Ll
 settings.api_use_responses_llama.desc = Use Responses API instead of ChatCompletions API in Chat with Files mode (LlamaIndex). OpenAI models only.
 settings.app.env = Application environment (os.environ)
 settings.app.env.desc = Additional environment vars to set on application start
+settings.audio.cache.enabled = Enable Cache
+settings.audio.cache.enabled.desc = Enable audio caching for speech synthesis generation.
+settings.audio.cache.max_files = Max files to store
+settings.audio.cache.max_files.desc = Max number of cached audio files stored to disk
 settings.audio.input.backend = Audio Input Backend
 settings.audio.input.backend.desc = Select the audio input backend.
 settings.audio.input.channels = Channels
@@ -1249,6 +1253,7 @@ settings.section.api_keys.openai = OpenAI
 settings.section.api_keys.perplexity = Perplexity
 settings.section.api_keys.xai = xAI
 settings.section.audio = Audio
+settings.section.audio.cache = Cache
 settings.section.audio.device = Devices
 settings.section.audio.options = Options
 settings.section.ctx = Context

pygpt_net/data/locale/locale.es.ini

@@ -1026,6 +1026,10 @@ settings.api_use_responses_llama = Usar Responses API en modo Chat con Archivos
 settings.api_use_responses_llama.desc = Usar Responses API en lugar de ChatCompletions API en modo Chat con Archivos (LlamaIndex). Solo modelos OpenAI.
 settings.app.env = Entorno de la aplicación (os.environ)
 settings.app.env.desc = Variables de entorno adicionales para configurar en el inicio de la aplicación
+settings.audio.cache.enabled = Habilitar caché
+settings.audio.cache.enabled.desc = Habilitar caché de audio para la generación de síntesis de voz.
+settings.audio.cache.max_files = Número máximo de archivos a almacenar
+settings.audio.cache.max_files.desc = Número máximo de archivos de audio en caché almacenados en el disco
 settings.audio.input.backend = Backend para la entrada de audio
 settings.audio.input.backend.desc = Selecciona el backend para la entrada de audio.
 settings.audio.input.channels = Canaux
@@ -1240,6 +1244,7 @@ settings.section.api_keys.openai = OpenAI
 settings.section.api_keys.perplexity = Perplexity
 settings.section.api_keys.xai = xAI
 settings.section.audio = Audio
+settings.section.audio.cache = Caché
 settings.section.audio.device = Dispositivos
 settings.section.audio.options = Opciones
 settings.section.ctx = Contexto

pygpt_net/data/locale/locale.fr.ini

@@ -1025,6 +1025,10 @@ settings.api_use_responses_llama = Utiliser Responses API en mode Chat avec des
 settings.api_use_responses_llama.desc = Utiliser Responses API au lieu de ChatCompletions API en mode Chat avec des Fichiers (LlamaIndex). Modèles OpenAI uniquement.
 settings.app.env = Environnement de l'application (os.environ)
 settings.app.env.desc = Variables d'environnement supplémentaires à définir au démarrage de l'application
+settings.audio.cache.enabled = Activer le cache
+settings.audio.cache.enabled.desc = Activer le cache audio pour la génération de synthèse vocale.
+settings.audio.cache.max_files = Nombre maximal de fichiers à stocker
+settings.audio.cache.max_files.desc = Nombre maximal de fichiers audio mis en cache et enregistrés sur le disque
 settings.audio.input.backend = Backend pour l'entrée audio
 settings.audio.input.backend.desc = Sélectionnez le backend pour l'entrée audio.
 settings.audio.input.channels = Canaux
@@ -1239,6 +1243,7 @@ settings.section.api_keys.openai = OpenAI
 settings.section.api_keys.perplexity = Perplexity
 settings.section.api_keys.xai = xAI
 settings.section.audio = Audio
+settings.section.audio.cache = Cache
 settings.section.audio.device = Appareils
 settings.section.audio.options = Options
 settings.section.ctx = Contexte

pygpt_net/data/locale/locale.it.ini

@@ -1025,6 +1025,10 @@ settings.api_use_responses_llama = Usa il Responses API in modalità Chat con Fi
 settings.api_use_responses_llama.desc = Usa il Responses API invece del ChatCompletions API in modalità Chat con File (LlamaIndex). Solo modelli OpenAI.
 settings.app.env = Ambiente dell'applicazione (os.environ)
 settings.app.env.desc = Variabili d'ambiente aggiuntive da impostare all'avvio dell'applicazione
+settings.audio.cache.enabled = Abilita cache
+settings.audio.cache.enabled.desc = Abilita la memorizzazione audio per la generazione della sintesi vocale.
+settings.audio.cache.max_files = Numero massimo di file da memorizzare
+settings.audio.cache.max_files.desc = Numero massimo di file audio in cache memorizzati su disco
 settings.audio.input.backend = Backend per l'ingresso audio
 settings.audio.input.backend.desc = Seleziona il backend per l'ingresso audio.
 settings.audio.input.channels = Canali
@@ -1239,6 +1243,7 @@ settings.section.api_keys.openai = OpenAI
 settings.section.api_keys.perplexity = Perplexity
 settings.section.api_keys.xai = xAI
 settings.section.audio = Audio
+settings.section.audio.cache = Cache
 settings.section.audio.device = Dispositivi
 settings.section.audio.options = Opzioni
 settings.section.ctx = Contesto

pygpt_net/data/locale/locale.pl.ini

@@ -1027,6 +1027,10 @@ settings.api_use_responses_llama = Używaj Responses API w trybie Chat z Plikami
 settings.api_use_responses_llama.desc = Używaj Responses API zamiast ChatCompletions API w trybie Chat z Plikami (LlamaIndex). Tylko modele OpenAI.
 settings.app.env = Środowisko aplikacji (os.environ)
 settings.app.env.desc = Dodatkowe zmienne środowiskowe do ustawienia przy starcie aplikacji
+settings.audio.cache.enabled = Włącz pamięć podręczną
+settings.audio.cache.enabled.desc = Włącz buforowanie audio dla generowania syntezy mowy.
+settings.audio.cache.max_files = Maksymalna liczba plików
+settings.audio.cache.max_files.desc = Maksymalna liczba plików audio w pamięci podręcznej zapisywanych na dysku
 settings.audio.input.backend = Backend dla wejścia audio
 settings.audio.input.backend.desc = Wybierz backend dla wejścia audio.
 settings.audio.input.channels = Kanały
@@ -1241,7 +1245,8 @@ settings.section.api_keys.openai = OpenAI
 settings.section.api_keys.perplexity = Perplexity
 settings.section.api_keys.xai = xAI
 settings.section.audio = Audio
-settings.section.audio.device = Urządzenia
+settings.section.audio.cache = Pamięć podręczna
+settings.section.audio.device = Urządzenia
 settings.section.audio.options = Opcje
 settings.section.ctx = Kontekst
 settings.section.developer = Deweloper

pygpt_net/data/locale/locale.uk.ini

@@ -1025,6 +1025,10 @@ settings.api_use_responses_llama = Використовувати Responses API
 settings.api_use_responses_llama.desc = Використовувати Responses API замість ChatCompletions API в режимі Чат з Файлами (LlamaIndex). Тільки моделі OpenAI.
 settings.app.env = Оточення додатка (os.environ)
 settings.app.env.desc = Додаткові змінні середовища для встановлення при запуску додатка
+settings.audio.cache.enabled = Увімкнути кеш
+settings.audio.cache.enabled.desc = Увімкнути кешування аудіо для генерації синтезу мови.
+settings.audio.cache.max_files = Максимальна кількість файлів для збереження
+settings.audio.cache.max_files.desc = Максимальна кількість кешованих аудіофайлів, збережених на диску
 settings.audio.input.backend = Бекенд для аудіовходу
 settings.audio.input.backend.desc = Виберіть бекенд для аудіовходу.
 settings.audio.input.channels = Канали
@@ -1239,6 +1243,7 @@ settings.section.api_keys.openai = OpenAI
 settings.section.api_keys.perplexity = Perplexity
 settings.section.api_keys.xai = xAI
 settings.section.audio = Аудіо
+settings.section.audio.cache = Кеш
 settings.section.audio.device = Пристрої
 settings.section.audio.options = Параметри
 settings.section.ctx = Контекст

pygpt_net/data/locale/locale.zh.ini

@@ -1025,6 +1025,10 @@ settings.api_use_responses_llama = 在Chat with Files模式（LlamaIndex）下
 settings.api_use_responses_llama.desc = 在Chat with Files模式（LlamaIndex）下使用Responses API而不是ChatCompletions API。仅限OpenAI模型。
 settings.app.env = 应用程序环境 (os.environ)
 settings.app.env.desc = 在应用程序启动时要设置的额外环境变量
+settings.audio.cache.enabled = 启用缓存
+settings.audio.cache.enabled.desc = 启用音频缓存以进行语音合成生成。
+settings.audio.cache.max_files = 要存储的最大文件数
+settings.audio.cache.max_files.desc = 缓存到磁盘的最大音频文件数
 settings.audio.input.backend = 音频输入的后端
 settings.audio.input.backend.desc = 选择音频输入的后端。
 settings.audio.input.channels = 声道
@@ -1239,6 +1243,7 @@ settings.section.api_keys.openai = OpenAI
 settings.section.api_keys.perplexity = Perplexity
 settings.section.api_keys.xai = xAI
 settings.section.audio = 音频
+settings.section.audio.cache = 缓存
 settings.section.audio.device = 设备
 settings.section.audio.options = 选项
 settings.section.ctx = 上下文

pygpt_net/plugin/audio_output/plugin.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.07 03:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 from typing import Any
@@ -176,6 +176,24 @@ class Plugin(BasePlugin):
             if not ctx.audio_read_allowed():
                 return  # abort if audio read is not allowed (commands, results, etc.)
 
+        # cache ctx
+        cache_enabled = self.window.core.config.get("audio.cache.enabled", False)
+        max_files = int(self.window.core.config.get("audio.cache.max_files", 10))
+        if cache_enabled:
+            # delete old if max
+            if max_files > 0:
+                self.window.core.audio.delete_old_cache(max_files)
+            if not cache_file:
+                # gen cache file path if exists
+                tmp_cache_file, is_cached = self.window.core.audio.prepare_cache_path(text)
+                if is_cached:
+                    event = Event(Event.AUDIO_PLAYBACK, ctx=ctx)
+                    event.data = {"audio_file": tmp_cache_file}
+                    return self.on_playback(ctx, event)  # playback cached audio file
+                else:
+                    if tmp_cache_file:
+                        cache_file = tmp_cache_file  # store cache file
+
         try:
             if text is not None and len(text) > 0:
                 self.stop_audio()
@@ -229,6 +247,8 @@ class Plugin(BasePlugin):
             worker.signals.stop.connect(self.handle_stop)
             worker.signals.volume_changed.connect(self.handle_volume)
 
+            self.window.controller.audio.on_begin("")
+
             backend = self.window.core.config.get("audio.output.backend", "native")
             if backend == "native":
                 worker.play()

pygpt_net/provider/audio_output/eleven_labs.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.02.25 01:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 import os
@@ -107,7 +107,7 @@ class ElevenLabsTextToSpeech(BaseProvider):
             for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
                 if chunk:
                     f.write(chunk)
-        return path
+        return str(path)
 
     def is_configured(self) -> bool:
         """

pygpt_net/provider/audio_output/google_tts.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.02.25 01:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 import json
 import os
@@ -108,7 +108,7 @@ class GoogleTextToSpeech(BaseProvider):
         content = json.loads(r.content)
         with open(path, "wb") as file:
             file.write(content.get("audioContent"))
-        return path
+        return str(path)
 
     def is_configured(self) -> bool:
         """

pygpt_net/provider/audio_output/ms_azure_tts.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.02.23 19:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 import os
@@ -111,7 +111,7 @@ class MSAzureTextToSpeech(BaseProvider):
         if response.status_code == 200:
             with open(path, "wb") as file:
                 file.write(response.content)
-            return path
+            return str(path)
 
     def is_configured(self) -> bool:
         """

pygpt_net/provider/audio_output/openai_tts.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2024.12.14 18:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 import os
@@ -79,7 +79,7 @@ class OpenAITextToSpeech(BaseProvider):
             input=text,
         )
         response.stream_to_file(path)
-        return path
+        return str(path)
 
     def is_configured(self) -> bool:
         """

pygpt_net/provider/core/config/json_file.py

@@ -55,13 +55,21 @@ class JsonFileProvider(BaseProvider):
                 shutil.copyfile(src, dst)
                 print("RECOVERY: Restored config file from base config: {}".format(src))
 
-        # data/tmp directory
+        # data tmp
         tmp_dir = os.path.join(self.window.core.config.get_user_dir('data'), 'tmp')
         if not os.path.exists(tmp_dir):
             try:
                 os.makedirs(tmp_dir, exist_ok=True)
             except Exception as e:
-                print("WARNING: Cannot create ``{}`` temp directory: {}".format(tmp_dir, e))
+                print("WARNING: Cannot create ``{}`` data temp directory: {}".format(tmp_dir, e))
+
+        # base tmp
+        tmp_dir = os.path.join(self.window.core.config.get_user_path(), 'tmp')
+        if not os.path.exists(tmp_dir):
+            try:
+                os.makedirs(tmp_dir, exist_ok=True)
+            except Exception as e:
+                print("WARNING: Cannot create ``{}`` base temp directory: {}".format(tmp_dir, e))
 
     def get_version(self) -> Optional[str]:
         """

pygpt_net/provider/core/config/patch.py

@@ -6,7 +6,7 @@
 # GitHub:  https://github.com/szczyglis-dev/py-gpt   #
 # MIT License                                        #
 # Created By  : Marcin Szczygliński                  #
-# Updated Date: 2025.08.07 03:00:00                  #
+# Updated Date: 2025.08.07 22:00:00                  #
 # ================================================== #
 
 import copy
@@ -2184,6 +2184,20 @@ class Patch:
                 self.window.core.updater.patch_css('web-blocks.light.css', True)  # force replace file
                 updated = True
 
+            # < 2.5.91
+            if old < parse_version("2.5.91"):
+                print("Migrating config from < 2.5.91...")
+                if "audio.cache.enabled" not in data:
+                    data["audio.cache.enabled"] = True
+                updated = True
+
+            # < 2.5.92
+            if old < parse_version("2.5.92"):
+                print("Migrating config from < 2.5.92...")
+                if "audio.cache.max_files" not in data:
+                    data["audio.cache.max_files"] = 1000
+                updated = True
+
         # update file
         migrated = False
         if updated:

pygpt_net/provider/core/model/patch.py

@@ -710,6 +710,17 @@ class Patch:
                             model.mode.remove("agent_openai")
                 updated = True
 
+            # <  2.5.91  <--- update names to models IDs
+            if old < parse_version("2.5.91"):
+                print("Migrating models from < 2.5.91...")
+                if "gpt-5" not in data:
+                    data["gpt-5"] = base_data["gpt-5"]
+                if "gpt-5-mini" not in data:
+                    data["gpt-5-mini"] = base_data["gpt-5-mini"]
+                if "gpt-5-nano" not in data:
+                    data["gpt-5-nano"] = base_data["gpt-5-nano"]
+                updated = True
+
         # update file
         if updated:
             data = dict(sorted(data.items()))

{pygpt_net-2.5.90.dist-info → pygpt_net-2.5.92.dist-info}/METADATA

@@ -1,9 +1,9 @@
 Metadata-Version: 2.3
 Name: pygpt-net
-Version: 2.5.90
-Summary: Desktop AI Assistant powered by: OpenAI o1, o3, GPT-4o, GPT-4 Vision, DALL-E 3, Llama 3, Mistral, Gemini, Claude, Grok, DeepSeek, Bielik, and other models supported by Llama Index, and Ollama. Chatbot, agents, completion, image generation, vision analysis, speech-to-text, plugins, internet access, file handling, command execution and more.
+Version: 2.5.92
+Summary: Desktop AI Assistant powered by: OpenAI GPT-5, o1, o3, GPT-4, Gemini, Claude, Grok, DeepSeek, and other models supported by Llama Index, and Ollama. Chatbot, agents, completion, image generation, vision analysis, speech-to-text, plugins, internet access, file handling, command execution and more.
 License: MIT
-Keywords: py_gpt,py-gpt,pygpt,desktop,app,o1,o3,gpt,gpt4,gpt-4o,gpt-4v,gpt3.5,gpt-4,gpt-4-vision,gpt-3.5,llama3,mistral,gemini,grok,deepseek,bielik,claude,tts,whisper,vision,chatgpt,dall-e,chat,chatbot,assistant,text completion,image generation,ai,api,openai,api key,langchain,llama-index,ollama,presets,ui,qt,pyside
+Keywords: py_gpt,py-gpt,pygpt,desktop,app,o1,o3,gpt-5,gpt,gpt4,gpt-4o,gpt-4v,gpt3.5,gpt-4,gpt-4-vision,gpt-3.5,llama3,mistral,gemini,grok,deepseek,bielik,claude,tts,whisper,vision,chatgpt,dall-e,chat,chatbot,assistant,text completion,image generation,ai,api,openai,api key,langchain,llama-index,ollama,presets,ui,qt,pyside
 Author: Marcin Szczyglinski
 Author-email: info@pygpt.net
 Requires-Python: >=3.10,<3.14
@@ -104,7 +104,7 @@ Description-Content-Type: text/markdown
 
 [![pygpt](https://snapcraft.io/pygpt/badge.svg)](https://snapcraft.io/pygpt)
 
-Release: **2.5.90** | build: **2025-08-07** | Python: **>=3.10, <3.14**
+Release: **2.5.92** | build: **2025-08-08** | Python: **>=3.10, <3.14**
 
 > Official website: https://pygpt.net | Documentation: https://pygpt.readthedocs.io
 > 
@@ -116,7 +116,7 @@ Release: **2.5.90** | build: **2025-08-07** | Python: **>=3.10, <3.14**
 
 ## Overview
 
-**PyGPT** is **all-in-one** Desktop AI Assistant that provides direct interaction with OpenAI language models, including `o1`, `o3`, `gpt-4o`, `gpt-4`, `gpt-4 Vision`, and `gpt-3.5`, through the `OpenAI API`. By utilizing `LlamaIndex`, the application also supports alternative LLMs, like those available on `HuggingFace`, locally available models via `Ollama` (like `Llama 3`,`Mistral`, `DeepSeek V3/R1` or `Bielik`), `Google Gemini`, `Anthropic Claude`, `Perplexity Sonar`, and `xAI Grok`.
+**PyGPT** is **all-in-one** Desktop AI Assistant that provides direct interaction with OpenAI language models, including `gpt-5`, `o1`, `o3`, `gpt-4o`, `gpt-4`, `gpt-4 Vision`, and `gpt-3.5`, through the `OpenAI API`. By utilizing `LlamaIndex`, the application also supports alternative LLMs, like those available on `HuggingFace`, locally available models via `Ollama` (like `Llama 3`,`Mistral`, `DeepSeek V3/R1` or `Bielik`), `Google Gemini`, `Anthropic Claude`, `Perplexity Sonar`, and `xAI Grok`.
 
 This assistant offers multiple modes of operation such as chat, assistants, completions, and image-related tasks using `DALL-E 3` for generation and `gpt-4 Vision` for image analysis. **PyGPT** has filesystem capabilities for file I/O, can generate and run Python code, execute system commands, execute custom commands and manage file transfers. It also allows models to perform web searches with the `Google` and `Microsoft Bing`.
 
@@ -145,7 +145,7 @@ You can download compiled 64-bit versions for Windows and Linux here: https://py
 - Desktop AI Assistant for `Linux`, `Windows` and `Mac`, written in Python.
 - Works similarly to `ChatGPT`, but locally (on a desktop computer).
 - 12 modes of operation: Chat, Chat with Files, Chat with Audio, Research (Perplexity), Completion, Image generation, Vision, Assistants, Experts, Computer use, Agents and Autonomous Mode.
-- Supports multiple models: `o1`, `o3`, `GPT-4o`, `GPT-4`, `GPT-3.5`, and any model accessible through `LlamaIndex` and `Ollama` such as `Llama 3`, `Mistral`, `Google Gemini`, `Anthropic Claude`, `xAI Grok`, `DeepSeek V3/R1`, `Perplexity Sonar`, `Bielik`, etc.
+- Supports multiple models: `gpt-5`, `o1`, `o3`, `GPT-4o`, `GPT-4`, `GPT-3.5`, and any model accessible through `LlamaIndex` and `Ollama` such as `Llama 3`, `Mistral`, `Google Gemini`, `Anthropic Claude`, `xAI Grok`, `DeepSeek V3/R1`, `Perplexity Sonar`, `Bielik`, etc.
 - Chat with your own Files: integrated `LlamaIndex` support: chat with data such as: `txt`, `pdf`, `csv`, `html`, `md`, `docx`, `json`, `epub`, `xlsx`, `xml`, webpages, `Google`, `GitHub`, video/audio, images and other data types, or use conversation history as additional context provided to the model.
 - Built-in vector databases support and automated files and data embedding.
 - Included support features for individuals with disabilities: customizable keyboard shortcuts, voice control, and translation of on-screen actions into audio via speech synthesis.
@@ -1181,6 +1181,9 @@ PyGPT has built-in support for models (as of 2025-07-26):
 - `gpt-4o-2024-11-20` (OpenAI)
 - `gpt-4o-audio-preview` (OpenAI)
 - `gpt-4o-mini` (OpenAI)
+- `gpt-5` (OpenAI)
+- `gpt-5-mini` (OpenAI)
+- `gpt-5-nano` (OpenAI)
 - `gpt-image-1` (OpenAI)
 - `grok-2-vision` (xAI)
 - `grok-3` (xAI)
@@ -3292,6 +3295,10 @@ Enable/disable remote tools, like Web Search or Image generation to use in OpenA
 
 - `Sampling Rate`: Sampling rate, default: 44100
 
+- `Use cache`: Use cache for generating audio files.
+
+- `Max files to store`: Max files to store on disk for audio cache.
+
 **Indexes / LlamaIndex**
 
 **General**
@@ -4351,6 +4358,15 @@ may consume additional tokens that are not displayed in the main window.
 
 ## Recent changes:
 
+**2.5.92 (2025-08-08)**
+
+- Added max files to store config option in Audio -> Cache.
+
+**2.5.91 (2025-08-08)**
+
+- Added GPT-5.
+- Added audio cache - #118.
+
 **2.5.90 (2025-08-07)**
 
 - Fix: Initialize context summary if a conversation starts with a tool call.

{pygpt_net-2.5.90.dist-info → pygpt_net-2.5.92.dist-info}/RECORD

@@ -1,6 +1,6 @@
-pygpt_net/CHANGELOG.txt,sha256=tR-VL3IzWyj381eB1wlv33rbQ6gfYvJA5t761DiY7S0,96644
+pygpt_net/CHANGELOG.txt,sha256=G4RISl9r-SJc1bsRAgeoUyUMokGlp1urYmOyeC_jzIE,96791
 pygpt_net/LICENSE,sha256=dz9sfFgYahvu2NZbx4C1xCsVn9GVer2wXcMkFRBvqzY,1146
-pygpt_net/__init__.py,sha256=6LY7TUV4-1DqyzazVedWML0FNJcIS7IizCOWO2a1SHc,1373
+pygpt_net/__init__.py,sha256=At2kiZ5ezKyU9mHK_GDNkheHFgl3buN3__yfacOt_EY,1373
 pygpt_net/app.py,sha256=86COG6F-sC9dIRURMjBPS4fkD3Zzrp5kwCFQuM4tikc,18971
 pygpt_net/config.py,sha256=FxN39zmTpOY84lgrfhfIDuxKmNPrePhNHdGxvEOKqK8,16881
 pygpt_net/container.py,sha256=4puHeSNIyj3q6gTjPLsQKE1U-4fAhoNANYKiDq-mTqA,4054
@@ -8,7 +8,7 @@ pygpt_net/controller/__init__.py,sha256=wtlkw4viFVuf2sP0iMSkK0jI1QMa3kcPfvQaqnC-
 pygpt_net/controller/access/__init__.py,sha256=_XZxGy5U93JGU49GbIB9E_I26_uRV_Zbz18lcp7u23A,510
 pygpt_net/controller/access/access.py,sha256=Q_p0ner14zKWjPC4Ug-V53IP9QrwJpefUMaed4g4aU4,2526
 pygpt_net/controller/access/control.py,sha256=nMGWzg60jNJMVAHIrism0_APzVMpbLAOcXG6mJuOSJ8,17332
-pygpt_net/controller/access/voice.py,sha256=26QKQ8HpHhn4EMwLv6bqZytafai9tlAZ6nn4Z-pA6ts,15819
+pygpt_net/controller/access/voice.py,sha256=UulM1KgqUQp601rlQoTTq7pZR4dcZOcn9JjKkPYDKPc,15757
 pygpt_net/controller/agent/__init__.py,sha256=GRKHllr8kuzoA2_rRHiQv27znsEcwLCiuNuU4G9xVZw,509
 pygpt_net/controller/agent/agent.py,sha256=bTlAVsJ5QPyQD525RwxV_yDiWyRZfAtTuspAdVN7hbA,1268
 pygpt_net/controller/agent/common.py,sha256=55CHhV-dsWeNe5QvdvNoyhEYVhQNrHt_Lv-VDTuiYRc,3871
@@ -25,7 +25,7 @@ pygpt_net/controller/assistant/threads.py,sha256=ShyV2pcuJHWMCWfCd0F5LTw3mc6A_4O
 pygpt_net/controller/attachment/__init__.py,sha256=-5owOyszPze-YLQuTtFLQnSwEj_ftTxFwAP_3jPNpss,514
 pygpt_net/controller/attachment/attachment.py,sha256=to7QK1PwvvkW6gBUxXFIm0R_wh9HrgW8raZf9dJgVmo,20397
 pygpt_net/controller/audio/__init__.py,sha256=Ci5ClV3DKuMCLtFqQEOr5qun--tlIzKkQlwj9ug_kI0,509
-pygpt_net/controller/audio/audio.py,sha256=kIHG_4ag6dbQ4hZOc5NdaPAreNXjlD7bZ9iFTrdXW4s,13643
+pygpt_net/controller/audio/audio.py,sha256=rUpibBGPGp1rLW3NJ46xQEqIAC-MyQ5mALSW6YbydQ0,13668
 pygpt_net/controller/calendar/__init__.py,sha256=AyzoNqYgxV35CMEzoi_SCSsQh4ehg_Wu_2nsK3xsbyg,512
 pygpt_net/controller/calendar/calendar.py,sha256=s55RkCFQPFzdDoQ2zp3kohlNdpiWxdSxQtsaROeiigw,4424
 pygpt_net/controller/calendar/note.py,sha256=y8Gkg35-aM1MfQ9P2NsRnmfSJw4Ps__9g6I1RhonR6s,11428
@@ -63,7 +63,7 @@ pygpt_net/controller/config/placeholder.py,sha256=ImlyuTtY_4__5I63peX3hshP6q1tXn
 pygpt_net/controller/ctx/__init__.py,sha256=0wH7ziC75WscBW8cxpeGBwEz5tolo_kCxGPoz2udI_E,507
 pygpt_net/controller/ctx/common.py,sha256=3W3jrsMmMWO9UHIRxfqd4Ob_eelRRCZng3_C3q7FCnQ,6534
 pygpt_net/controller/ctx/ctx.py,sha256=nmWrsxm7ZlucB5tGDHkkCQEUDsdaDedru-0NUYkARlo,38609
-pygpt_net/controller/ctx/extra.py,sha256=Otjo10XLBZzKQ-bYAJg5u9h8xVGGmFBEFIglIOn6vXI,8859
+pygpt_net/controller/ctx/extra.py,sha256=WApWjnIfl3SoI0VZVbptvjjqhFPJl-dSfqW12tlBHrY,8599
 pygpt_net/controller/ctx/summarizer.py,sha256=dO-LqIclwI7gIot1yjNo9eZ0HxakWCSoqePORgCLOk8,3072
 pygpt_net/controller/debug/__init__.py,sha256=dOJGTICjvTtrPIEDOsxCzcOHsfu8AFPLpSKbdN0q0KI,509
 pygpt_net/controller/debug/debug.py,sha256=NGYj3e-OJ07h9weyw51sHe-txnWNWaSDGI5ofZe202U,8821
@@ -82,7 +82,7 @@ pygpt_net/controller/idx/idx.py,sha256=h8k8vGaPEl2ikA0vMrOT7RGY3XrhEpNjeHHxEUBLq
 pygpt_net/controller/idx/indexer.py,sha256=xW4ruWNpoGnyfFMTU2wOfuk63RRWBFgZGKIqiDlQoA8,22347
 pygpt_net/controller/idx/settings.py,sha256=orWd8ARxIBBs3MWJLjEKcqmrXLi6DvsLitsPvPd2fXU,7916
 pygpt_net/controller/kernel/__init__.py,sha256=XVS7uaC0VZZkpjqkbs6pqSwXdAZWLnR3dVNCHmF7XH4,510
-pygpt_net/controller/kernel/kernel.py,sha256=AO-fvrthyYCbe20TlvuwnnH_JsHO5264qnAxz8cum1Y,12967
+pygpt_net/controller/kernel/kernel.py,sha256=XP7ymz72dxiOMdigwR3uYyf6V1NAoW9KNxhHKBKKqO8,12999
 pygpt_net/controller/kernel/reply.py,sha256=eGt5bM7tUFXsXKm0XxNaGzUx145G9Ew_6B88W_SX_C8,6287
 pygpt_net/controller/kernel/stack.py,sha256=HJh7jkLEYQxUHJigbjD7sJh3FvvqUTCevqGf3doc29I,4046
 pygpt_net/controller/lang/__init__.py,sha256=Bpr9Ygoi_vd_CnfbQiZzYAeg9KV0vqNIuMl8EWmHKaM,508
@@ -168,9 +168,9 @@ pygpt_net/core/attachments/attachments.py,sha256=bUqvfPqlpdXiGf3GvS1kTE45A0Q1Eo3
 pygpt_net/core/attachments/context.py,sha256=S67zDh4lD9_stmeeh1ZGNv3IMt_6_IMGxq-3Jqn9kMs,25119
 pygpt_net/core/attachments/worker.py,sha256=Yt6DU2Yr7-FPTPTdlj8vDzT46pcKcvZoatiZybY6YEo,1685
 pygpt_net/core/audio/__init__.py,sha256=SNShKpjqXzLhaSKxWiM8b6lasHRkrdSZ8ck-X7RJ-VY,509
-pygpt_net/core/audio/audio.py,sha256=Gk284ejJsRK-_ydTwBbNOF6jHRMtYsZ-M4lF3CX20TU,4816
+pygpt_net/core/audio/audio.py,sha256=_WaS1JHT9S3BqmzEc7bOcWwMfth6ueMJQVs13jzoy4c,7709
 pygpt_net/core/audio/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-pygpt_net/core/audio/backend/native.py,sha256=zujWrXz9ZNpwFXw4tCl6j8MNbeez5tS9tJvkOzwQN7g,20008
+pygpt_net/core/audio/backend/native.py,sha256=HfkuK281CByBGQgxv343mRC-pyyxWfZrhYfcYTTEYOg,22117
 pygpt_net/core/audio/backend/pyaudio.py,sha256=iVpkr-82OldSY_9Zar9U7hMiiBcy9kZso4h8Xcvo9pA,18487
 pygpt_net/core/audio/backend/pygame.py,sha256=mFNzv3ADcjxcTkHpM08Xdp3ZmxYHrnZPdKvFs6gWoSk,16814
 pygpt_net/core/audio/capture.py,sha256=Ka2jsNEzhAMqF1vmF9wqYHxT20r1XY9_8f44HcwQ0CE,3797
@@ -340,8 +340,8 @@ 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=z44tI4VjcgDW0jYrqxN8QrmBkp2stE0qlPuil0JWmrw,24686
-pygpt_net/data/config/models.json,sha256=93-itPLPadsGqjnlf05UVxh4V3Z8jyaVDoiSUpbt02Y,104302
+pygpt_net/data/config/config.json,sha256=-lndyyNRWW_Ahdr3KSmaehRc6f7kgJ2FSELQ7IMtNx4,24750
+pygpt_net/data/config/models.json,sha256=avI6jlTtphXMgA7U29aIY25srKvttoTC_Fzw3InCqwM,109127
 pygpt_net/data/config/modes.json,sha256=M882iiqX_R2sNQl9cqZ3k-uneEvO9wpARtHRMLx_LHw,2265
 pygpt_net/data/config/presets/agent_code_act.json,sha256=GYHqhxtKFLUCvRI3IJAJ7Qe1k8yD9wGGNwManldWzlI,754
 pygpt_net/data/config/presets/agent_openai.json,sha256=vMTR-soRBiEZrpJJHuFLWyx8a3Ez_BqtqjyXgxCAM_Q,733
@@ -374,7 +374,7 @@ pygpt_net/data/config/presets/current.vision.json,sha256=x1ll5B3ROSKYQA6l27PRGXU
 pygpt_net/data/config/presets/dalle_white_cat.json,sha256=esqUb43cqY8dAo7B5u99tRC0MBV5lmlrVLnJhTSkL8w,552
 pygpt_net/data/config/presets/joke_agent.json,sha256=R6n9P7KRb0s-vZWZE7kHdlOfXAx1yYrPmUw8uLyw8OE,474
 pygpt_net/data/config/presets/joke_expert.json,sha256=jjcoIYEOaEp8kLoIbecxQROiq4J3Zess5w8_HmngPOY,671
-pygpt_net/data/config/settings.json,sha256=9imY03YwU5LtOZGinAliy3Cp39h7D7cvE7ozeIas4sQ,64171
+pygpt_net/data/config/settings.json,sha256=9QTRQDJMijDtQPBYeXB5MDjMFMbdXOKsNFU820i6QS0,64821
 pygpt_net/data/config/settings_section.json,sha256=Ng6kgmgxVmvt-KYFIqZvIDAEK4DfISNjNVF55DFWNjs,1082
 pygpt_net/data/css/fix_windows.css,sha256=Mks14Vg25ncbMqZJfAMStrhvZmgHF6kU75ohTWRZeI8,664
 pygpt_net/data/css/fix_windows.dark.css,sha256=7hGbT_qI5tphYC_WlFpJRDAcmjBb0AQ2Yc-y-_Zzf2M,161
@@ -1597,14 +1597,14 @@ pygpt_net/data/js/katex/fonts/KaTeX_Typewriter-Regular.woff,sha256=4U_tArGrp86fW
 pygpt_net/data/js/katex/fonts/KaTeX_Typewriter-Regular.woff2,sha256=cdUX1ngneHz6vfGGkUzDNY7aU543kxlB8rL9SiH2jAs,13568
 pygpt_net/data/js/katex/katex.min.css,sha256=lVaKnUaQNG4pI71WHffQZVALLQF4LMZEk4nOia8U9ow,23532
 pygpt_net/data/js/katex/katex.min.js,sha256=KLASOtKS2x8pUxWVzCDmlWJ4jhuLb0vtrgakbD6gDDo,276757
-pygpt_net/data/locale/locale.de.ini,sha256=0_UQYSyEQ0IqTpaHl-OtDU1IhpXlkjbzUdN-D5DA_vg,94938
-pygpt_net/data/locale/locale.en.ini,sha256=oFFhqeyj1njU39eNYTDFkxbizxUtCOGn38b8n5H7so0,86148
-pygpt_net/data/locale/locale.es.ini,sha256=IhrRh_grMooCSYj9GLzydWKRqUH_4BGDEvYwRvG1SM4,95693
-pygpt_net/data/locale/locale.fr.ini,sha256=2xKiEaCJhVmhQttPEQi7nW2KaNIn7JIDO6uTGvBeDWk,98140
-pygpt_net/data/locale/locale.it.ini,sha256=IsMjpgm4QPxwrXb7ndJEN8ClG548T6Scdj_2Yb6bVaw,93531
-pygpt_net/data/locale/locale.pl.ini,sha256=uUrH_7JNzwaniZFM84TONSxCZ6vnFU04qB3NQyll-eI,93258
-pygpt_net/data/locale/locale.uk.ini,sha256=C5Y_2C8jAD8ABZlOxOmXNMcjy0vNULAej5ho064ippA,129629
-pygpt_net/data/locale/locale.zh.ini,sha256=63zhP-WN-HoapipZ6yjbJgwdaipyWdxNIKt2WgxpskE,83503
+pygpt_net/data/locale/locale.de.ini,sha256=ZpYsSFQk-0-XHUGjJSjOd8g6Y49MbJYo89xmulHwg4A,95311
+pygpt_net/data/locale/locale.en.ini,sha256=QWHYX0HTzRua3HXDHi7uyCFLv1M9xBd8QOG7SS8r9bU,86457
+pygpt_net/data/locale/locale.es.ini,sha256=JTh5fcDTBd4l3RYe2PuiW9sRniq-Nux6oHPD3dfTGfo,96064
+pygpt_net/data/locale/locale.fr.ini,sha256=gOpc07xXNOzkKgMEmhCYnU4Zef4FOuDXBNZF920FKME,98511
+pygpt_net/data/locale/locale.it.ini,sha256=eU5uJ8rAvPB8VWTaWmKosO6CK028pN4MXrDaS5l93Sk,93890
+pygpt_net/data/locale/locale.pl.ini,sha256=1OoPSQnak3PTEndaxnmNHQeyzdNEarbz5gxwM-GIJmY,93640
+pygpt_net/data/locale/locale.uk.ini,sha256=FIbXUrfl6yuMf77mS5hz5wG60gB31CdQA6z7KA_yuXk,130136
+pygpt_net/data/locale/locale.zh.ini,sha256=Ns_BD1pj7nAmEzuSJiskHsrGOg3UdNw3DOr-s7ZGv3I,83809
 pygpt_net/data/locale/plugin.agent.de.ini,sha256=BY28KpfFvgfVYJzcw2o5ScWnR4uuErIYGyc3NVHlmTw,1714
 pygpt_net/data/locale/plugin.agent.en.ini,sha256=HwOWCI7e8uzlIgyRWRVyr1x6Xzs8Xjv5pfEc7jfLOo4,1728
 pygpt_net/data/locale/plugin.agent.es.ini,sha256=bqaJQne8HPKFVtZ8Ukzo1TSqVW41yhYbGUqW3j2x1p8,1680
@@ -1829,7 +1829,7 @@ pygpt_net/plugin/audio_input/simple.py,sha256=rSqczTMzNbmMNNWGbt9j2M837szWRJpa_1
 pygpt_net/plugin/audio_input/worker.py,sha256=-VmSUfsFl--95G9aHKOm9LqDw6F9-8HHS7ckAzcBW6A,12157
 pygpt_net/plugin/audio_output/__init__.py,sha256=UglI8YPtzF_-buENrR0vqDuvzlK3CJdIXKx-iaJozZM,510
 pygpt_net/plugin/audio_output/config.py,sha256=IA2K-9fQMZSwYGyi30Uh5qAlYwuqwaHo3dtDJ13vQdo,1208
-pygpt_net/plugin/audio_output/plugin.py,sha256=ai4_ToNwUydeAsTwrT-_1v95c9b2TFh6QM1k-3TeLCU,9332
+pygpt_net/plugin/audio_output/plugin.py,sha256=tncu3gPVVYZYF173ggnytuEh1AKDnUMUAlPDvZvu41Y,10276
 pygpt_net/plugin/audio_output/worker.py,sha256=XhkY0uYlx1UIuAeWB3CA9MLvvDxI870E0iKJ0O2Lx10,3718
 pygpt_net/plugin/base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pygpt_net/plugin/base/config.py,sha256=q5WAcF-h3KZH4bJFYANasM7UmV1v1c43fF1EZ05iF7Y,848
@@ -1950,10 +1950,10 @@ pygpt_net/provider/audio_input/openai_whisper.py,sha256=QABdVR4cC0VxKGLQyMJNnG6w
 pygpt_net/provider/audio_input/openai_whisper_local.py,sha256=fkz8zvTgscJeNJ6Hkr0mS0IHE3tOTRqaZ7bgpOxV3p8,3129
 pygpt_net/provider/audio_output/__init__.py,sha256=lOkgAiuNUqkAl_QrIG3ZsUznIZeJYtokgzEnDB8gRic,488
 pygpt_net/provider/audio_output/base.py,sha256=1z3vuwUYOOzUD24GNZN_CyeO_VOhFUA35adpXAnXPHk,2002
-pygpt_net/provider/audio_output/eleven_labs.py,sha256=RW1p2S0v9P2RVOtxeyKlzvgwCdD5jJTMir_h6v5nKkc,4231
-pygpt_net/provider/audio_output/google_tts.py,sha256=qkJBJMTJSDXo1y_QOpuMW0Aj09c7EDzyqBHrNTAwI0w,4286
-pygpt_net/provider/audio_output/ms_azure_tts.py,sha256=zdfgAjriF8bh88wNL-G8hrPcPG9r4182hK_ibtQJ9C4,4960
-pygpt_net/provider/audio_output/openai_tts.py,sha256=StpX5eJ-fLKfV_wDNdA5z6CJ_rWdJD8jbTBzL26Phec,3005
+pygpt_net/provider/audio_output/eleven_labs.py,sha256=XN6-iZYOowbiWLNK9oBWW2DxT4DPWj6AQhA7P6xI1bM,4236
+pygpt_net/provider/audio_output/google_tts.py,sha256=4VMNBR4O8srUNTkdjuQn8jHmOdFV3XZIbrmMOdmAtAo,4291
+pygpt_net/provider/audio_output/ms_azure_tts.py,sha256=-8YlUwzUruR1cX6N5EZZfZSLOlOGbCvyHXTDwDD9GAg,4965
+pygpt_net/provider/audio_output/openai_tts.py,sha256=RauqWXxJ-aHc4by5462w0yOpZv5Ta1a9KhoS-8sMEqo,3010
 pygpt_net/provider/core/__init__.py,sha256=YHQ86AUqjoP79N5vRqOmK-6FUDLQhCl_0y6Z4Tun3dU,488
 pygpt_net/provider/core/assistant/__init__.py,sha256=jQQgG9u_ZLsZWXustoc1uvC-abUvj4RBKPAM30-f2Kc,488
 pygpt_net/provider/core/assistant/base.py,sha256=zFJs4LxnBvUBri9-FgOYjv1wyfDFEzEu9H01GcTYL0s,1251
@@ -1984,8 +1984,8 @@ pygpt_net/provider/core/calendar/db_sqlite/provider.py,sha256=Q78xHqxIhnjukQmLIS
 pygpt_net/provider/core/calendar/db_sqlite/storage.py,sha256=QDclQCQdr4QyRIqjgGXHBdHLbikJGqNhLlsEopMInDc,11204
 pygpt_net/provider/core/config/__init__.py,sha256=jQQgG9u_ZLsZWXustoc1uvC-abUvj4RBKPAM30-f2Kc,488
 pygpt_net/provider/core/config/base.py,sha256=cbvzbMNqL2XgC-36gGubnU37t94AX7LEw0lecb2Nm80,1365
-pygpt_net/provider/core/config/json_file.py,sha256=fQHjoVIPYdW7kl3fe0uNl7f5fMU76hoJK72qx_yKY9o,6453
-pygpt_net/provider/core/config/patch.py,sha256=QwsceOLEafvDgJlHXq5AhrSheesvrsj3StVXqcpPCwU,115173
+pygpt_net/provider/core/config/json_file.py,sha256=GCcpCRQnBiSLWwlGbG9T3ZgiHkTfp5Jsg2KYkZcakBw,6789
+pygpt_net/provider/core/config/patch.py,sha256=xpTeLYRky7k77RtWD7XOhsEbWSoHKWXEps9FSjlDC7k,115715
 pygpt_net/provider/core/ctx/__init__.py,sha256=jQQgG9u_ZLsZWXustoc1uvC-abUvj4RBKPAM30-f2Kc,488
 pygpt_net/provider/core/ctx/base.py,sha256=Tfb4MDNe9BXXPU3lbzpdYwJF9S1oa2-mzgu5XT4It9g,3003
 pygpt_net/provider/core/ctx/db_sqlite/__init__.py,sha256=0dP8VhI4bnFsQQKxAkaleKFlyaMycDD_cnE7gBCa57Y,512
@@ -2014,7 +2014,7 @@ pygpt_net/provider/core/mode/patch.py,sha256=VS2KCYW05jxLd-lcStNY1k4fHKUUrVVLTdR
 pygpt_net/provider/core/model/__init__.py,sha256=jQQgG9u_ZLsZWXustoc1uvC-abUvj4RBKPAM30-f2Kc,488
 pygpt_net/provider/core/model/base.py,sha256=L1x2rHha8a8hnCUYxZr88utay1EWEx5qBXW_2acpAN0,1319
 pygpt_net/provider/core/model/json_file.py,sha256=l74l_n5PEHNp-FsoHtO9LHflz3RFKwDwKwOKN0stgZw,8418
-pygpt_net/provider/core/model/patch.py,sha256=s7tVHsUMVcHvZpaGFC15rVkE6M85PozP3RKs8yQEp48,33152
+pygpt_net/provider/core/model/patch.py,sha256=O_i0f0ixxObgMaZOZwBwF6hzRmZeujKHP07qBkTpeGQ,33661
 pygpt_net/provider/core/notepad/__init__.py,sha256=jQQgG9u_ZLsZWXustoc1uvC-abUvj4RBKPAM30-f2Kc,488
 pygpt_net/provider/core/notepad/base.py,sha256=7aPhild8cALTaN3JEbI0YrkIW1DRIycGQWTfsdH6WcQ,1323
 pygpt_net/provider/core/notepad/db_sqlite/__init__.py,sha256=0dP8VhI4bnFsQQKxAkaleKFlyaMycDD_cnE7gBCa57Y,512
@@ -2379,8 +2379,8 @@ pygpt_net/ui/widget/textarea/web.py,sha256=7VTiA1LwWSUmbJ7r1uhKV-RFndOfNC_r_EAJi
 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=mQ_9Esbs2htAw82tPG5rzST8IZwXFwO2eLPsHRTCMJ4,6936
-pygpt_net-2.5.90.dist-info/LICENSE,sha256=rbPqNB_xxANH8hKayJyIcTwD4bj4Y2G-Mcm85r1OImM,1126
-pygpt_net-2.5.90.dist-info/METADATA,sha256=3KEd-zfK2BFlVHQb1J8hanO_xzKxnv0142kA2g4ZsnI,182637
-pygpt_net-2.5.90.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-pygpt_net-2.5.90.dist-info/entry_points.txt,sha256=qvpII6UHIt8XfokmQWnCYQrTgty8FeJ9hJvOuUFCN-8,43
-pygpt_net-2.5.90.dist-info/RECORD,,
+pygpt_net-2.5.92.dist-info/LICENSE,sha256=rbPqNB_xxANH8hKayJyIcTwD4bj4Y2G-Mcm85r1OImM,1126
+pygpt_net-2.5.92.dist-info/METADATA,sha256=cVNv0QesYPCO_rSvTPxFcQXMVw33rAayvRC2Tt8lqoo,182962
+pygpt_net-2.5.92.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+pygpt_net-2.5.92.dist-info/entry_points.txt,sha256=qvpII6UHIt8XfokmQWnCYQrTgty8FeJ9hJvOuUFCN-8,43
+pygpt_net-2.5.92.dist-info/RECORD,,