Fix SAPI 4 driver

source/config/configSpec.py

@@ -1,5 +1,5 @@
 # A part of NonVisual Desktop Access (NVDA)
-# Copyright (C) 2006-2024 NV Access Limited, Babbage B.V., Davy Kager, Bill Dengler, Julien Cochuyt,
+# Copyright (C) 2006-2025 NV Access Limited, Babbage B.V., Davy Kager, Bill Dengler, Julien Cochuyt,
 # Joseph Lee, Dawid Pieper, mltony, Bram Duvigneau, Cyrille Bougot, Rob Meredith,
 # Burman's Computer and Education Ltd., Leonard de Ruijter, Łukasz Golonka
 # This file is covered by the GNU General Public License.
@@ -45,6 +45,7 @@
 	autoDialectSwitching = boolean(default=false)
 	delayedCharacterDescriptions = boolean(default=false)
 	excludedSpeechModes = int_list(default=list())
+	_hasSapi4WarningBeenShown = boolean(default=False)
 
 	[[__many__]]
 		capPitchChange = integer(default=30,min=-100,max=100)

source/speech/speech.py

@@ -1,7 +1,7 @@
 # A part of NonVisual Desktop Access (NVDA)
 # This file is covered by the GNU General Public License.
 # See the file COPYING for more details.
-# Copyright (C) 2006-2024 NV Access Limited, Peter Vágner, Aleksey Sadovoy, Babbage B.V., Bill Dengler,
+# Copyright (C) 2006-2025 NV Access Limited, Peter Vágner, Aleksey Sadovoy, Babbage B.V., Bill Dengler,
 # Julien Cochuyt, Derek Riemer, Cyrille Bougot, Leonard de Ruijter, Łukasz Golonka
 
 """High-level functions to speak information."""
@@ -11,14 +11,18 @@
 import weakref
 import unicodedata
 import time
+
 import colors
 import api
 from annotation import _AnnotationRolesT
 import controlTypes
 from controlTypes import OutputReason, TextPosition
 from controlTypes.state import State
+import globalVars
+from gui.message import MessageDialog
+import queueHandler
 import tones
-from synthDriverHandler import getSynth
+from synthDriverHandler import SynthDriver, getSynth, synthChanged
 import re
 import textInfos
 import speechDictHandler
@@ -3059,3 +3063,41 @@ def clearTypedWordBuffer() -> None:
 	complete the word (such as a focus change or choosing to move the caret).
 	"""
 	_curWordChars.clear()
+
+
+def _sapi4DeprecationWarning(synth: SynthDriver, audioOutputDevice: str, isFallback: bool):
+	"""A synthChanged event handler to alert the user about the deprecation of SAPI4."""
+
+	def setShown():
+		config.conf["speech"]["_hasSapi4WarningBeenShown"] = True
+
+	def impl():
+		MessageDialog(
+			parent=None,
+			message=_(
+				# Translators: Message warning users that SAPI4 is deprecated.
+				"Microsoft Speech API version 4 is obsolete. "
+				"Using this speech synthesizer may pose a security risk. "
+				"This synthesizer driver will be removed in NVDA 2026.1. "
+				"You are strongly encouraged to choose a more modern speech synthesizer.",
+			),
+			# Translators: Title of a message dialog.
+			title=_("Warning"),
+			buttons=None,
+		).addOkButton(
+			callback=setShown,
+		).Show()
+
+	if (
+		(not isFallback)
+		and (synth.name == "sapi4")
+		and (not config.conf["speech"]["_hasSapi4WarningBeenShown"])
+	):
+		# We need to queue the dialog to appear, as wx may not have been initialised the first time this is called.
+		queueHandler.queueFunction(queueHandler.eventQueue, impl)
+
+
+if not globalVars.appArgs.minimal:
+	# Don't warn users about SAPI4 deprecation in minimal mode.
+	# This stops the dialog appearing on secure screens or in the launcher.
+	synthChanged.register(_sapi4DeprecationWarning)

source/synthDrivers/_sapi4.py

@@ -1,7 +1,5 @@
-# _sapi4.py
-# Contributed by Serotek Corporation under the GPL
 # A part of NonVisual Desktop Access (NVDA)
-# Copyright (C) 2006-2008 NVDA Contributors <http://www.nvda-project.org/>
+# Copyright (C) 2006-2025 NV Access Limited, Serotek Corporation
 # This file is covered by the GNU General Public License.
 # See the file COPYING for more details.
 
@@ -20,6 +18,7 @@
 	Structure,
 )
 from ctypes.wintypes import BYTE, DWORD, LPCWSTR, WORD
+from enum import IntEnum
 from comtypes import GUID, IUnknown, STDMETHOD
 
 import winKernel
@@ -227,3 +226,19 @@ class ITTSNotifySinkW(IUnknown):
 
 CLSID_MMAudioDest = GUID("{CB96B400-C743-11cd-80E5-00AA003E4B50}")
 CLSID_TTSEnumerator = GUID("{D67C0280-C743-11cd-80E5-00AA003E4B50}")
+
+
+# Defined in mmsyscom.h
+MMSYSERR_NOERROR = 0
+
+
+class DriverMessage(IntEnum):
+	"""WaveOutMessage message codes
+	Defined in mmddk.h
+	"""
+
+	QUERY__INSTANCE_ID = 2065
+	"""DRV_QUERYFUNCTIONINSTANCEID """
+
+	QUERY_INSTANCE_ID_SIZE = 2066
+	"""DRV_QUERYFUNCTIONINSTANCEIDSIZE """

source/synthDrivers/sapi4.py

@@ -1,18 +1,21 @@
 # A part of NonVisual Desktop Access (NVDA)
-# Copyright (C) 2006-2024 NV Access Limited, Leonard de Ruijter
+# Copyright (C) 2006-2025 NV Access Limited, Leonard de Ruijter
 # This file is covered by the GNU General Public License.
 # See the file COPYING for more details.
+# This module is deprecated, pending removal in NVDA 2026.1.
 
 import locale
 from collections import OrderedDict
 import winreg
 from comtypes import CoCreateInstance, COMObject, COMError, GUID
-from ctypes import byref, c_ulong, POINTER
-from ctypes.wintypes import DWORD, WORD
+from ctypes import byref, c_ulong, POINTER, c_wchar, create_string_buffer, sizeof, windll
+from ctypes.wintypes import DWORD, HANDLE, WORD
 from typing import Optional
 from synthDriverHandler import SynthDriver, VoiceInfo, synthIndexReached, synthDoneSpeaking
 from logHandler import log
+import warnings
 from ._sapi4 import (
+	MMSYSERR_NOERROR,
 	CLSID_MMAudioDest,
 	CLSID_TTSEnumerator,
 	IAudioMultiMediaDevice,
@@ -33,9 +36,9 @@
 	TTSFEATURE_VOLUME,
 	TTSMODEINFO,
 	VOICECHARSET,
+	DriverMessage,
 )
 import config
-import nvwave
 import weakref
 
 from speech.commands import (
@@ -51,6 +54,9 @@
 from speech.types import SpeechSequence
 
 
+warnings.warn("synthDrivers.sapi4 is deprecated, pending removal in NVDA 2026.1.", DeprecationWarning)
+
+
 class SynthDriverBufSink(COMObject):
 	_com_interfaces_ = [ITTSBufNotifySink]
 
@@ -233,7 +239,7 @@ def _set_voice(self, val):
 			raise ValueError("no such mode: %s" % val)
 		self._currentMode = mode
 		self._ttsAudio = CoCreateInstance(CLSID_MMAudioDest, IAudioMultiMediaDevice)
-		self._ttsAudio.DeviceNumSet(nvwave.outputDeviceNameToID(config.conf["audio"]["outputDevice"], True))
+		self._ttsAudio.DeviceNumSet(_mmDeviceEndpointIdToWaveOutId(config.conf["audio"]["outputDevice"]))
 		self._ttsCentral = POINTER(ITTSCentralW)()
 		self._ttsEngines.Select(self._currentMode.gModeID, byref(self._ttsCentral), self._ttsAudio)
 		self._ttsAttrs = self._ttsCentral.QueryInterface(ITTSAttributes)
@@ -365,3 +371,49 @@ def _set_volume(self, val: int):
 		# using the low word for the left channel and the high word for the right channel.
 		val |= val << 16
 		self._ttsAttrs.VolumeSet(val)
+
+
+def _mmDeviceEndpointIdToWaveOutId(targetEndpointId: str) -> int:
+	"""Translate from an MMDevice Endpoint ID string to a WaveOut Device ID number.
+
+	:param targetEndpointId: MMDevice endpoint ID string to translate from, or the default value of the `audio.outputDevice` configuration key for the default output device.
+	:return: An integer WaveOut device ID for use with SAPI4.
+		If no matching device is found, or the default output device is requested, `-1` is returned, which means output will be handled by Microsoft Sound Mapper.
+	"""
+	if targetEndpointId != config.conf.getConfigValidation(("audio", "outputDevice")).default:
+		targetEndpointIdByteCount = (len(targetEndpointId) + 1) * sizeof(c_wchar)
+		currEndpointId = create_string_buffer(targetEndpointIdByteCount)
+		currEndpointIdByteCount = DWORD()
+		# Defined in mmeapi.h
+		winmm = windll.winmm
+		waveOutMessage = winmm.waveOutMessage
+		waveOutGetNumDevs = winmm.waveOutGetNumDevs
+		for devID in range(waveOutGetNumDevs()):
+			# Get the length of this device's endpoint ID string.
+			mmr = waveOutMessage(
+				HANDLE(devID),
+				DriverMessage.QUERY_INSTANCE_ID_SIZE,
+				byref(currEndpointIdByteCount),
+				None,
+			)
+			if (mmr != MMSYSERR_NOERROR) or (currEndpointIdByteCount.value != targetEndpointIdByteCount):
+				# ID lengths don't match, so this device can't be a match.
+				continue
+			# Get the device's endpoint ID string.
+			mmr = waveOutMessage(
+				HANDLE(devID),
+				DriverMessage.QUERY__INSTANCE_ID,
+				byref(currEndpointId),
+				currEndpointIdByteCount,
+			)
+			if mmr != MMSYSERR_NOERROR:
+				continue
+			# Decode the endpoint ID string to a python string, and strip the null terminator.
+			if (
+				currEndpointId.raw[: targetEndpointIdByteCount - sizeof(c_wchar)].decode("utf-16")
+				== targetEndpointId
+			):
+				return devID
+	# No matching device found, or default requested explicitly.
+	# Return the ID of Microsoft Sound Mapper
+	return -1

user_docs/en/changes.md

@@ -4,6 +4,9 @@
 
 ### Important notes
 
+* The support for Microsoft Speech API version 4 synthesizers is planned for removal in NVDA 2026.1.
+Any remaining users of SAPI4 speech synthesizers are encouraged to choose a more modern speech synthesizer. (#17599)
+
 ### New Features
 
 * Support for math in PDFs has been added.
@@ -179,6 +182,7 @@ Use `gui.message.MessageDialog` instead. (#17582)
   * `NoConsoleOptionParser`, `stringToBool`, `stringToLang` in `__main__`; use the same symbols in `argsParsing` instead.
   * `__main__.parser`; use `argsParsing.getParser()` instead.
 * `bdDetect.DeviceType` is deprecated in favour of `bdDetect.ProtocolType` and `bdDetect.CommunicationType` to take into account the fact that both HID and Serial communication can take place over USB and Bluetooth. (#17537 , @LeonarddeR)
+* SAPI4, `synthDrivers.sapi4`, is deprecated and planned for removal in 2026.1. (#17599)
 
 ## 2024.4.2
 

user_docs/en/userGuide.md

@@ -3883,6 +3883,7 @@ There are also many variants which can be chosen to alter the sound of the voice
 SAPI 4 is an older Microsoft standard for software speech synthesizers.
 NVDA still supports this for users who already have SAPI 4 synthesizers installed.
 However, Microsoft no longer support this and needed components are no longer available from Microsoft.
+Support for SAPI4 will be removed in NVDA 2026.1.
 
 When using this synthesizer with NVDA, the available voices (accessed from the [Speech category](#SpeechSettings) of the [NVDA Settings](#NVDASettings) dialog or by the [Synth Settings Ring](#SynthSettingsRing)) will contain all the voices from all the installed SAPI 4 engines found on your system.