125:
interfaces (for example, the loading of grammar from a file is done in the runtime, but then the grammar data is passed to the recognition engine to actually use in recognition). The recognition and synthesis engines also generate events while processing (for example, to indicate an utterance has been recognized or to indicate word boundaries in the synthesized speech). These pass in the reverse direction, from the engines, through the runtime DLL, and on to an
77:
In general, all versions of the API have been designed such that a software developer can write an application to perform speech recognition and synthesis by using a standard set of interfaces, accessible from a variety of programming languages. In addition, it is possible for a 3rd-party company to
626:
The existing SAPI 5 API can also be used from managed code to a limited extent by creating a COM Interop code (helper code designed to assist in accessing COM interfaces and classes). This works well in some scenarios however the new API should provide a more seamless experience equivalent to using
335:
The design of the new API included the concept of strictly separating the application and engine so all calls were routed through the runtime sapi.dll. This change was intended to make the API more 'engine-independent', preventing applications from inadvertently depending on features of a specific
89:
There have been two main 'families' of the
Microsoft Speech API. SAPI versions 1 through 4 are all similar to each other, with extra features in each newer version. SAPI 5, however, was a completely new interface, released in 2000. Since then several sub-versions of this API have been released.
124:
Typically in SAPI 5 applications issue calls through the API (for example to load a recognition grammar; start recognition; or provide text to be synthesized). The sapi.dll runtime component interprets these commands and processes them, where necessary calling on the engine through the engine
415:
versions. In the U.S. English system, special acoustic models were available for children's speech and telephony speech. The synthesis engine was available in
English and Chinese. This version of the API and recognition engines also shipped in Microsoft Office XP in 2001.
389:. The runtime includes objects for performing speech input from the microphone or speech output to speakers (or any sound device); as well as to and from wave files. It is also possible to write a custom audio object to stream audio to or from a non-standard location.
85:
In general, the Speech API is a freely redistributable component which can be shipped with any
Windows application that wishes to use speech technology. Many versions (although not all) of the speech recognition and synthesis engines are also freely redistributable.
410:
This version shipped in late 2000 as part of the Speech SDK version 5.0, together with version 5.0 recognition and synthesis engines. The recognition engines supported continuous dictation and command & control and were released in U.S. English, Japanese and
361:). All applications using the shared recognizer communicate with this single instance. This allows sharing of resources, removes contention for the microphone and allows for a global UI for control of all speech applications.
522:
User-Specified shortcuts in lexicons, which is the ability to add a string to the lexicon and associate it with a shortcut word. When dictating, the user can say the shortcut word and the recognizer will return the expanded
232:. This version included low-level Direct Speech Recognition and Direct Text To Speech APIs which applications could use to directly control engines, as well as simplified 'higher-level' Voice Command and Voice Talk APIs.
331:
runtime was released in 2000. This was a complete redesign from previous versions and neither engines nor applications which used older versions of SAPI could use the new version without considerable modification.
464:
mark-up languages, as well as additional server features and performance improvements. The Speech Server also shipped with the version 6 desktop recognition engine and the version 7 server recognition engine.
683:
Speech recognition support for 8 languages at release time: U.S. English, U.K. English, traditional
Chinese, simplified Chinese, Japanese, Spanish, French, and German, with more language to be released
1084:
634:
which lead to memory fragmentation and exclude the use of the library in any non-trivial applications. As a workaround, Microsoft has suggested using a different API, which has fewer voices.
336:
engine. In addition, this change was aimed at making it much easier to incorporate speech technology into an application by moving some management and initialization code into the runtime.
424:
This version shipped in late 2001 as part of the Speech SDK version 5.1. Automation-compliant interfaces were added to the API to allow use from Visual Basic, scripting languages such as
82:
engines or adapt existing engines to work with SAPI. In principle, as long as these engines conform to the defined interfaces they can be used instead of the
Microsoft-supplied engines.
377:
markup for specifying a grammar, as well as mechanisms to create them dynamically in code. Methods also exist for instructing the recognizer to load a built-in dictation language model.
383:. This performs speech synthesis, producing an audio stream from a text. A markup language (similar to XML, but not strictly XML) can be used for controlling the synthesis process.
240:
SAPI 3.0 was released in 1997. It added limited support for dictation speech recognition (discrete speech, not continuous), and additional sample applications and audio sources.
401:. This is a concept allowing recognition and TTS engines, audio objects, lexicons and other categories of an object to be registered, enumerated and instantiated in a common way.
339:
The new API was initially a pure COM API and could be used easily only from C/C++. Support for VB and scripting languages were added later. Operating systems from
395:. This allows custom words and pronunciations to be added by a user or application. These are added to the recognition or synthesis engine's built-in lexicons.
2493:
193:- implementations of the necessary engine interfaces but with no true speech processing which could be used as a sample for those porting an engine to SAPI.
1000:
110:
which applications and engines conformed to. Applications could also use simplified higher-level objects rather than directly call methods on the engines.
1449:
968:
264:
development. This was shipped as part of an SDK that included recognition and synthesis engines. It also shipped (with synthesis engines only) in
367:. For applications that require explicit control of the recognition process, the in-proc recognizer object can be used instead of the shared one.
1424:
132:
In addition to the actual API definition and runtime DLL, other components are shipped with all versions of SAPI to make a complete Speech
1485:
1004:
106:(recognition and synthesis). In SAPI versions 1 to 4, applications could directly communicate with engines. The API included an abstract
2206:
1958:
1033:
983:
1075:
607:. It has similar functionality to SAPI 5 but is more suitable to be used by managed code applications. The new API is available on
497:
457:
1444:
1158:
1038:
588:
580:
1823:
1674:
1434:
1533:
1459:
493:(SSML) version 1.0 provides the ability to mark up voice characteristics, speed, volume, pitch, emphasis, and pronunciation.
1568:
630:
However, major obstacle towards transitioning from the COM Interop is the fact that the managed implementation has subtle
587:
2006 and later versions. The
Chinese version of Vista and later Windows client versions also include a female voice named
2498:
2018:
1727:
929:
54:
applications. To date, a number of versions of the API have been released, which have shipped either as part of a Speech
1028:
2276:
1619:
1591:
1518:
1194:
956:
1818:
1795:
924:
35:
845:
includes SAPI 5.1 and speech recognition engines 6.1 for
English, Japanese, and Chinese (simplified and traditional)
121:). There is an API implemented by this component which applications use, and another set of interfaces for engines.
2353:
2049:
2014:
1856:
1770:
1490:
1344:
490:
461:
515:
Support for semantic interpretation script within grammars. SAPI 5.3 enables an SRGS grammar to be annotated with
113:
In SAPI 5 however, applications and engines do not directly communicate with each other. Instead, each talks to a
2271:
2115:
1780:
1153:
1123:
554:
357:. For desktop speech recognition applications, a recognizer object can be used that runs in a separate process (
1951:
1872:
1813:
507:
882:
1684:
583:
which replaces
Microsoft Sam and sounds more natural and intelligible. It is also installed on Windows XP by
440:
and Office 2003 also include this version but with a substantially improved version 6 recognition engine and
1808:
1679:
1669:
1657:
1068:
842:
584:
437:
2009:
1920:
1833:
1785:
744:
Later versions of SAPI 5 (e.g. SAPI 5.3 and above) are compatible with the following operating systems:
373:. Speech grammars are used to specify the words that the recognizer is listening for. SAPI 5 defines an
271:
The main components of the SAPI 4 API (which were all available in C++, COM, and ActiveX flavors) were:
2266:
1662:
1429:
1396:
1230:
848:
643:
478:
2503:
2281:
1944:
1652:
1454:
1371:
1148:
1143:
1118:
1581:
2251:
2095:
1629:
1417:
1381:
948:
911:
656:
503:
It does not support the use of SRGS to specify dual-tone modulated-frequency (touch-tone) grammars.
133:
55:
2442:
2327:
2196:
2181:
1915:
1900:
1877:
1624:
1614:
1548:
1061:
876:
453:
71:
2437:
2391:
1576:
1558:
1528:
1386:
1098:
249:
2406:
2145:
2028:
1846:
1765:
1760:
1553:
1313:
1225:
1128:
20:
559:
Microsoft Sam (Speech
Articulation Module) is a commonly shipped SAPI 5 voice. In addition,
2401:
2068:
1647:
1349:
1298:
1138:
905:
804:
564:
8:
1722:
1705:
1606:
1513:
1252:
798:
756:
752:
711:
620:
612:
441:
136:. The following components are among those included in most versions of the Speech SDK:
2421:
2411:
2322:
1293:
1133:
858:
604:
481:
is now integrated into the operating system, the Speech SDK and APIs are a part of the
412:
98:
The Speech API can be viewed as an interface or piece of middleware which sits between
43:
2386:
1905:
1775:
1717:
1543:
1323:
1277:
51:
2261:
2211:
1967:
1376:
1262:
864:
560:
178:
79:
63:
59:
47:
873:
2002, Microsoft Excel 2003, and
Microsoft Excel 2007 for speaking spreadsheet data
2105:
1257:
1043:
972:
870:
688:
229:
114:
67:
1053:
2452:
1737:
1596:
1318:
1189:
1044:
Microsoft Systems Journal Whitepaper by Mike Rozak on the first version of SAPI
825:
748:
737:
672:
500:(SRGS) supports the definition of context-free grammars, with two limitations:
896:, a text-to-speech application that reads text aloud from a variety of sources
2487:
2472:
2462:
2381:
2125:
1975:
1851:
1841:
1755:
1639:
1508:
1439:
1272:
1267:
852:
786:
648:
616:
576:
474:
208:
2467:
2416:
2256:
2085:
1910:
887:
815:
727:
677:
600:
429:
265:
261:
248:
SAPI 4.0 was released in 1998. This version of SAPI included both the core
1039:
Microsoft download site for Speech API Software Developers Kit version 5.1
662:
New tutorial, microphone wizard, and UI for controlling speech recognition
532:
Version 8 of the speech recognition engine ("Microsoft Speech Recognizer")
2396:
2312:
2120:
1999:
1895:
1803:
1538:
1242:
1184:
1179:
899:
771:
631:
482:
2231:
2337:
2302:
2201:
2191:
2130:
1523:
1464:
1328:
1247:
893:
830:
820:
810:
766:
761:
732:
722:
716:
608:
526:
Additional functionality and ease-of-programming provided by new types.
516:
489:
Support for W3C XML speech grammars for recognition and synthesis. The
433:
340:
225:
957:"Speech synthesis and recognition in .NET - Give applications a voice"
691:
most notably, and all other Microsoft speech applications use SAPI 5.
567:
Michael and Michelle voices. The SAPI 5.1 SDK installs 2 more voices,
2332:
2176:
2155:
2150:
2004:
1925:
781:
776:
542:
224:
The first version of SAPI was released in 1995, and was supported on
39:
159:- to select and configure default speech recognizer and synthesizer.
2363:
2307:
2226:
2221:
2140:
2100:
1994:
1936:
1308:
1108:
1103:
699:
The Speech API is compatible with the following operating systems:
177:
to allow developers to package the engines and runtime with their
2090:
2023:
1750:
1745:
1710:
1586:
1412:
1354:
1303:
1220:
1204:
425:
278:- high-level objects for command & control speech recognition
257:
284:- high-level objects for continuous dictation speech recognition
2447:
2317:
2044:
1990:
1364:
1237:
1048:
740:, Service Pack 6a, in English, Japanese and Simplified Chinese.
344:
519:
for semantic interpretation to supplement the recognized text.
2457:
2358:
2286:
2186:
2160:
2135:
2054:
1391:
934:
529:
Performance improvements, improved reliability, and security.
253:
651:
includes a number of new speech-related features including:
2216:
1480:
1359:
1163:
1113:
144:
452:
This was a special version of the API for use only in the
432:. This version of the API and TTS engines were shipped in
19:
This article is about the Speech API. For other uses, see
1689:
374:
256:
wrapper classes to make programming from C++ easier; and
211:
was a key person who led Microsoft's early SAPI efforts.
1029:
Microsoft Cognitive Services Ignite 2018 event blog post
637:
477:
together with new recognition and synthesis engines. As
16:
Application programming interface for Microsoft Windows
883:
Microsoft Plus! Voice Command for Windows Media Player
668:
Built-in updated Speech Recognition engine (Version 8)
994:
992:
984:
System. Speech has a memory leak | Microsoft Connect
541:
This is an updated version of the API that ships in
861:
in Windows 2000 and later Windows operating systems
296:- objects for writing telephone speech applications
302:- objects for direct control of recognition engine
1083:
998:
989:
986:. Connect.microsoft.com. Retrieved on 2013-09-27.
314:- for reading to and from an audio device or file
2485:
836:
485:. SAPI 5.3 includes the following new features:
308:- objects for direct control of synthesis engine
665:New version of the Speech API runtime: SAPI 5.3
1952:
1069:
473:This is the version of the API that ships in
2494:Microsoft application programming interfaces
914:(NVDA), a free and open source screen reader
456:which shipped in 2004. It added support for
181:to produce a single installable application.
671:New Speech Synthesis engine and SAPI voice
62:itself. Applications that use SAPI include
1959:
1945:
1728:Security Support Provider Interface (SSPI)
1076:
1062:
937: – Microsoft's Speech Application SDK
890:uses voice output to read document content
594:
290:- high-level objects for speech synthesis
78:produce their own Speech Recognition and
954:
879:for Windows Pocket PC and Windows Mobile
498:Speech Recognition Grammar Specification
28:Speech Application Programming Interface
1159:Windows Advanced Rasterization Platform
2486:
1154:DirectX Graphics Infrastructure (DXGI)
843:Microsoft Windows XP Tablet PC Edition
214:
1940:
1057:
638:Speech functionality in Windows Vista
93:
1966:
811:Microsoft Windows Millennium Edition
723:Microsoft Windows Millennium Edition
318:
930:List of speech recognition software
655:Speech control of the full Windows
350:Major features of the API include:
13:
2277:Texas Instruments LPC Speech Chips
1620:Microsoft Foundation Classes (MFC)
1592:Distributed Component Object Model
719:(Home Edition, Professional, etc.)
14:
2515:
1022:
925:Comparison of speech synthesizers
2354:Speech Synthesis Markup Language
2015:Festival Speech Synthesis System
694:
627:any other managed code library.
548:
491:Speech Synthesis Markup Language
260:controls to allow drag-and-drop
2116:Microsoft text-to-speech voices
680:speech API (codenamed SpeechFX)
555:Microsoft text-to-speech voices
1630:Windows Template Library (WTL)
977:
1:
1625:Active Template Library (ATL)
1345:Data Access Components (MDAC)
1085:Microsoft APIs and frameworks
941:
837:Major applications using SAPI
799:Microsoft Windows Server 2003
712:Microsoft Windows Server 2003
707:List as of SAPI version 5.1:
585:Microsoft Streets & Trips
563:XP and Office 2003 installed
147:and as C or C++ header files.
438:Windows XP Tablet PC Edition
7:
1921:Multilingual User Interface
1847:Dynamic Data Exchange (DDE)
918:
792:
536:
468:
447:
419:
405:
203:
10:
2520:
2499:Speech processing software
1049:Microsoft Speech Team blog
1001:"SAPI System Requirements"
849:Windows Speech Recognition
644:Windows Speech Recognition
641:
552:
508:Augmented Backus–Naur form
479:Windows Speech Recognition
175:Redistributable components
169:Speech Recognition engines
58:or as part of the Windows
18:
2430:
2372:
2346:
2295:
2282:General Instrument SP0256
2244:
2169:
2078:
2067:
2037:
1983:
1974:
1886:
1865:
1832:
1794:
1736:
1698:
1638:
1605:
1567:
1499:
1473:
1405:
1372:Extensible Storage Engine
1337:
1286:
1213:
1172:
1149:Windows Imaging Component
1144:Windows Image Acquisition
1091:
702:
603:API ships as part of the
300:Direct Speech Recognition
243:
235:
219:
2096:Software Automatic Mouth
959:. Redmond Developer News
912:NonVisual Desktop Access
826:Microsoft Windows NT 4.0
749:Microsoft Windows Server
738:Microsoft Windows NT 4.0
347:upwards were supported.
134:Software Development Kit
2443:Concatenative synthesis
2328:Microsoft Speech Server
2197:NIAONiao Virtual Singer
1916:Language Interface Pack
1901:Text Services Framework
1615:Framework Class Library
1034:Microsoft site for SAPI
999:Microsoft Corporation.
971:14 January 2010 at the
877:Microsoft Voice Command
787:Microsoft Windows Vista
595:Managed code Speech API
454:Microsoft Speech Server
185:Sample application code
72:Microsoft Speech Server
2438:Articulatory synthesis
2392:Franklin Seaney Cooper
1559:Common Log File System
1387:Access Database Engine
1099:Desktop Window Manager
1003:. MSDN. Archived from
816:Microsoft Windows 2000
728:Microsoft Windows 2000
325:Speech SDK version 5.0
171:in multiple languages.
165:in multiple languages.
163:Text-To-Speech engines
2407:Wolfgang von Kempelen
2187:CeVIO Creative Studio
2146:CeVIO Creative Studio
2029:Automatik Text Reader
1887:Text and multilingual
772:Microsoft Windows 8.1
306:Direct Text To Speech
21:SAPI (disambiguation)
2402:Haskins Laboratories
2111:Microsoft Speech API
1873:Active Accessibility
1139:Windows Color System
831:Microsoft Windows 95
821:Microsoft Windows 98
805:Microsoft Windows XP
767:Microsoft Windows 10
762:Microsoft Windows 11
733:Microsoft Windows 98
717:Microsoft Windows XP
506:It does not support
327:, incorporating the
157:Control Panel applet
141:API definition files
129:in the application.
108:interface definition
42:to allow the use of
1911:Input method editor
1723:Data Protection API
1514:Windows Script Host
1253:Image Mastering API
782:Microsoft Windows 7
777:Microsoft Windows 8
621:Windows Server 2008
613:Windows Server 2003
442:Traditional Chinese
393:User lexicon object
252:API; together with
215:SAPI 1-4 API family
2412:Ignatius Mattingly
1809:Enterprise Library
1796:Software factories
1500:Administration and
1430:Filtering Platform
1231:Video Acceleration
867:XP and Office 2003
859:Microsoft Narrator
605:.NET Framework 3.0
413:Simplified Chinese
365:In-proc recognizer
151:Runtime components
94:Basic architecture
44:speech recognition
2481:
2480:
2387:Catherine Browman
2240:
2239:
2063:
2062:
2050:Lyricos / Flinger
1934:
1933:
1906:Text Object Model
1718:Windows CardSpace
1544:Windows Installer
1278:Video for Windows
355:Shared Recognizer
319:SAPI 5 API family
2511:
2504:Voice technology
2323:Windows Narrator
2262:Pattern playback
2212:Symphonic Choirs
2076:
2075:
1981:
1980:
1968:Speech synthesis
1961:
1954:
1947:
1938:
1937:
1519:WMI (extensions)
1377:Entity Framework
1263:Media Foundation
1114:D3D (extensions)
1078:
1071:
1064:
1055:
1054:
1016:
1015:
1013:
1012:
996:
987:
981:
975:
967:
965:
964:
952:
865:Microsoft Office
659:and applications
561:Microsoft Office
387:Audio interfaces
179:application code
153:- e.g. sapi.dll.
64:Microsoft Office
48:speech synthesis
2519:
2518:
2514:
2513:
2512:
2510:
2509:
2508:
2484:
2483:
2482:
2477:
2426:
2374:
2368:
2342:
2291:
2236:
2165:
2106:Microsoft Agent
2070:
2059:
2033:
1970:
1965:
1935:
1930:
1888:
1882:
1861:
1828:
1790:
1732:
1694:
1634:
1601:
1569:Component model
1563:
1549:Error Reporting
1501:
1495:
1469:
1401:
1333:
1324:SideBar Gadgets
1282:
1258:Managed DirectX
1209:
1168:
1092:Graphics and UI
1087:
1082:
1025:
1020:
1019:
1010:
1008:
997:
990:
982:
978:
973:Wayback Machine
962:
960:
953:
949:
944:
921:
871:Microsoft Excel
839:
795:
705:
697:
689:Microsoft Agent
646:
640:
597:
557:
551:
539:
471:
450:
422:
408:
371:Grammar objects
321:
294:Voice Telephony
282:Voice Dictation
246:
238:
230:Windows NT 3.51
222:
217:
206:
96:
68:Microsoft Agent
24:
17:
12:
11:
5:
2517:
2507:
2506:
2501:
2496:
2479:
2478:
2476:
2475:
2470:
2465:
2460:
2455:
2453:Inverse filter
2450:
2445:
2440:
2434:
2432:
2428:
2427:
2425:
2424:
2419:
2414:
2409:
2404:
2399:
2394:
2389:
2384:
2378:
2376:
2370:
2369:
2367:
2366:
2361:
2356:
2350:
2348:
2344:
2343:
2341:
2340:
2335:
2330:
2325:
2320:
2315:
2310:
2305:
2299:
2297:
2293:
2292:
2290:
2289:
2284:
2279:
2274:
2269:
2264:
2259:
2254:
2248:
2246:
2242:
2241:
2238:
2237:
2235:
2234:
2229:
2224:
2219:
2214:
2209:
2204:
2199:
2194:
2189:
2184:
2179:
2173:
2171:
2167:
2166:
2164:
2163:
2158:
2153:
2148:
2143:
2138:
2133:
2128:
2123:
2118:
2113:
2108:
2103:
2098:
2093:
2088:
2082:
2080:
2073:
2065:
2064:
2061:
2060:
2058:
2057:
2052:
2047:
2041:
2039:
2035:
2034:
2032:
2031:
2026:
2021:
2012:
2007:
2002:
1997:
1987:
1985:
1978:
1972:
1971:
1964:
1963:
1956:
1949:
1941:
1932:
1931:
1929:
1928:
1923:
1918:
1913:
1908:
1903:
1898:
1892:
1890:
1884:
1883:
1881:
1880:
1875:
1869:
1867:
1863:
1862:
1860:
1859:
1854:
1849:
1844:
1838:
1836:
1830:
1829:
1827:
1826:
1821:
1816:
1811:
1806:
1800:
1798:
1792:
1791:
1789:
1788:
1783:
1778:
1773:
1768:
1763:
1758:
1753:
1748:
1742:
1740:
1734:
1733:
1731:
1730:
1725:
1720:
1715:
1714:
1713:
1702:
1700:
1696:
1695:
1693:
1692:
1687:
1682:
1677:
1672:
1667:
1666:
1665:
1660:
1650:
1644:
1642:
1640:Device drivers
1636:
1635:
1633:
1632:
1627:
1622:
1617:
1611:
1609:
1603:
1602:
1600:
1599:
1597:.NET Framework
1594:
1589:
1584:
1579:
1573:
1571:
1565:
1564:
1562:
1561:
1556:
1551:
1546:
1541:
1536:
1531:
1529:Task Scheduler
1526:
1521:
1516:
1511:
1505:
1503:
1497:
1496:
1494:
1493:
1488:
1483:
1477:
1475:
1471:
1470:
1468:
1467:
1462:
1457:
1452:
1447:
1442:
1437:
1432:
1427:
1425:Winsock Kernel
1422:
1421:
1420:
1409:
1407:
1403:
1402:
1400:
1399:
1394:
1389:
1384:
1382:Sync Framework
1379:
1374:
1369:
1368:
1367:
1362:
1357:
1352:
1341:
1339:
1335:
1334:
1332:
1331:
1326:
1321:
1316:
1311:
1306:
1301:
1296:
1290:
1288:
1284:
1283:
1281:
1280:
1275:
1270:
1265:
1260:
1255:
1250:
1245:
1240:
1235:
1234:
1233:
1228:
1217:
1215:
1211:
1210:
1208:
1207:
1202:
1197:
1192:
1190:DirectX plugin
1187:
1182:
1176:
1174:
1170:
1169:
1167:
1166:
1161:
1156:
1151:
1146:
1141:
1136:
1131:
1126:
1121:
1116:
1111:
1106:
1101:
1095:
1093:
1089:
1088:
1081:
1080:
1073:
1066:
1058:
1052:
1051:
1046:
1041:
1036:
1031:
1024:
1023:External links
1021:
1018:
1017:
988:
976:
955:Michael Dunn.
946:
945:
943:
940:
939:
938:
932:
927:
920:
917:
916:
915:
909:
903:
897:
891:
885:
880:
874:
868:
862:
856:
846:
838:
835:
834:
833:
828:
823:
818:
813:
808:
802:
794:
791:
790:
789:
784:
779:
774:
769:
764:
759:
751:releases from
742:
741:
735:
730:
725:
720:
714:
704:
701:
696:
693:
686:
685:
681:
675:
673:Microsoft Anna
669:
666:
663:
660:
639:
636:
596:
593:
589:Microsoft Lili
581:Microsoft Anna
553:Main article:
550:
547:
538:
535:
534:
533:
530:
527:
524:
520:
513:
512:
511:
504:
494:
470:
467:
449:
446:
421:
418:
407:
404:
403:
402:
396:
390:
384:
378:
368:
362:
320:
317:
316:
315:
309:
303:
297:
291:
285:
279:
245:
242:
237:
234:
221:
218:
216:
213:
205:
202:
201:
200:
194:
191:Sample engines
188:
182:
172:
166:
160:
154:
148:
95:
92:
80:Text-To-Speech
15:
9:
6:
4:
3:
2:
2516:
2505:
2502:
2500:
2497:
2495:
2492:
2491:
2489:
2474:
2473:Voice cloning
2471:
2469:
2466:
2464:
2463:Phase vocoder
2461:
2459:
2456:
2454:
2451:
2449:
2446:
2444:
2441:
2439:
2436:
2435:
2433:
2429:
2423:
2420:
2418:
2415:
2413:
2410:
2408:
2405:
2403:
2400:
2398:
2395:
2393:
2390:
2388:
2385:
2383:
2382:Alan W. Black
2380:
2379:
2377:
2371:
2365:
2362:
2360:
2357:
2355:
2352:
2351:
2349:
2345:
2339:
2336:
2334:
2331:
2329:
2326:
2324:
2321:
2319:
2316:
2314:
2311:
2309:
2306:
2304:
2301:
2300:
2298:
2294:
2288:
2285:
2283:
2280:
2278:
2275:
2273:
2270:
2268:
2265:
2263:
2260:
2258:
2255:
2253:
2250:
2249:
2247:
2243:
2233:
2230:
2228:
2225:
2223:
2220:
2218:
2215:
2213:
2210:
2208:
2205:
2203:
2200:
2198:
2195:
2193:
2190:
2188:
2185:
2183:
2180:
2178:
2175:
2174:
2172:
2168:
2162:
2159:
2157:
2154:
2152:
2149:
2147:
2144:
2142:
2139:
2137:
2134:
2132:
2129:
2127:
2126:Voice browser
2124:
2122:
2119:
2117:
2114:
2112:
2109:
2107:
2104:
2102:
2099:
2097:
2094:
2092:
2089:
2087:
2084:
2083:
2081:
2077:
2074:
2072:
2066:
2056:
2053:
2051:
2048:
2046:
2043:
2042:
2040:
2036:
2030:
2027:
2025:
2022:
2020:
2016:
2013:
2011:
2008:
2006:
2003:
2001:
1998:
1996:
1992:
1989:
1988:
1986:
1982:
1979:
1977:
1976:Free software
1973:
1969:
1962:
1957:
1955:
1950:
1948:
1943:
1942:
1939:
1927:
1924:
1922:
1919:
1917:
1914:
1912:
1909:
1907:
1904:
1902:
1899:
1897:
1894:
1893:
1891:
1885:
1879:
1878:UI Automation
1876:
1874:
1871:
1870:
1868:
1866:Accessibility
1864:
1858:
1855:
1853:
1850:
1848:
1845:
1843:
1840:
1839:
1837:
1835:
1831:
1825:
1822:
1820:
1817:
1815:
1812:
1810:
1807:
1805:
1802:
1801:
1799:
1797:
1793:
1787:
1784:
1782:
1779:
1777:
1774:
1772:
1769:
1767:
1764:
1762:
1759:
1757:
1754:
1752:
1749:
1747:
1744:
1743:
1741:
1739:
1735:
1729:
1726:
1724:
1721:
1719:
1716:
1712:
1709:
1708:
1707:
1704:
1703:
1701:
1697:
1691:
1688:
1686:
1683:
1681:
1678:
1676:
1673:
1671:
1668:
1664:
1661:
1659:
1656:
1655:
1654:
1651:
1649:
1646:
1645:
1643:
1641:
1637:
1631:
1628:
1626:
1623:
1621:
1618:
1616:
1613:
1612:
1610:
1608:
1604:
1598:
1595:
1593:
1590:
1588:
1585:
1583:
1580:
1578:
1575:
1574:
1572:
1570:
1566:
1560:
1557:
1555:
1552:
1550:
1547:
1545:
1542:
1540:
1537:
1535:
1534:Offline Files
1532:
1530:
1527:
1525:
1522:
1520:
1517:
1515:
1512:
1510:
1509:Win32 console
1507:
1506:
1504:
1498:
1492:
1489:
1487:
1486:Telephony API
1484:
1482:
1481:Messaging API
1479:
1478:
1476:
1474:Communication
1472:
1466:
1463:
1461:
1458:
1456:
1453:
1451:
1448:
1446:
1443:
1441:
1440:Windows Rally
1438:
1436:
1433:
1431:
1428:
1426:
1423:
1419:
1416:
1415:
1414:
1411:
1410:
1408:
1404:
1398:
1395:
1393:
1390:
1388:
1385:
1383:
1380:
1378:
1375:
1373:
1370:
1366:
1363:
1361:
1358:
1356:
1353:
1351:
1348:
1347:
1346:
1343:
1342:
1340:
1336:
1330:
1327:
1325:
1322:
1320:
1317:
1315:
1312:
1310:
1307:
1305:
1302:
1300:
1297:
1295:
1292:
1291:
1289:
1285:
1279:
1276:
1274:
1273:Windows Media
1271:
1269:
1266:
1264:
1261:
1259:
1256:
1254:
1251:
1249:
1246:
1244:
1241:
1239:
1236:
1232:
1229:
1227:
1226:Media Objects
1224:
1223:
1222:
1219:
1218:
1216:
1212:
1206:
1203:
1201:
1198:
1196:
1193:
1191:
1188:
1186:
1183:
1181:
1178:
1177:
1175:
1171:
1165:
1162:
1160:
1157:
1155:
1152:
1150:
1147:
1145:
1142:
1140:
1137:
1135:
1132:
1130:
1127:
1125:
1122:
1120:
1117:
1115:
1112:
1110:
1107:
1105:
1102:
1100:
1097:
1096:
1094:
1090:
1086:
1079:
1074:
1072:
1067:
1065:
1060:
1059:
1056:
1050:
1047:
1045:
1042:
1040:
1037:
1035:
1032:
1030:
1027:
1026:
1007:on 2007-05-04
1006:
1002:
995:
993:
985:
980:
974:
970:
958:
951:
947:
936:
933:
931:
928:
926:
923:
922:
913:
910:
908:screen reader
907:
904:
902:screen reader
901:
898:
895:
892:
889:
886:
884:
881:
878:
875:
872:
869:
866:
863:
860:
857:
854:
853:Windows Vista
850:
847:
844:
841:
840:
832:
829:
827:
824:
822:
819:
817:
814:
812:
809:
806:
803:
800:
797:
796:
788:
785:
783:
780:
778:
775:
773:
770:
768:
765:
763:
760:
758:
754:
750:
747:
746:
745:
739:
736:
734:
731:
729:
726:
724:
721:
718:
715:
713:
710:
709:
708:
700:
695:Compatibility
692:
690:
682:
679:
676:
674:
670:
667:
664:
661:
658:
654:
653:
652:
650:
649:Windows Vista
645:
635:
633:
628:
624:
622:
618:
617:Windows Vista
614:
610:
606:
602:
592:
590:
586:
582:
578:
577:Windows Vista
574:
570:
566:
562:
556:
549:SAPI 5 Voices
546:
544:
531:
528:
525:
521:
518:
514:
509:
505:
502:
501:
499:
495:
492:
488:
487:
486:
484:
480:
476:
475:Windows Vista
466:
463:
459:
455:
445:
443:
439:
435:
431:
427:
417:
414:
400:
399:Object tokens
397:
394:
391:
388:
385:
382:
379:
376:
372:
369:
366:
363:
360:
356:
353:
352:
351:
348:
346:
342:
337:
333:
330:
326:
313:
312:Audio objects
310:
307:
304:
301:
298:
295:
292:
289:
286:
283:
280:
277:
276:Voice Command
274:
273:
272:
269:
267:
263:
259:
255:
251:
241:
233:
231:
227:
212:
210:
209:Xuedong Huang
198:
197:Documentation
195:
192:
189:
186:
183:
180:
176:
173:
170:
167:
164:
161:
158:
155:
152:
149:
146:
142:
139:
138:
137:
135:
130:
128:
122:
120:
116:
111:
109:
105:
101:
91:
87:
83:
81:
75:
73:
69:
65:
61:
57:
53:
49:
45:
41:
38:developed by
37:
33:
29:
22:
2468:Self-voicing
2417:Philip Rubin
2296:Applications
2257:Mockingboard
2110:
2086:Amazon Polly
2069:Proprietary
1814:Composite UI
1299:RSS Platform
1199:
1009:. Retrieved
1005:the original
979:
961:. Retrieved
950:
888:Adobe Reader
743:
706:
698:
687:
678:Managed code
647:
632:memory leaks
629:
625:
601:managed code
598:
572:
568:
558:
540:
472:
451:
430:managed code
423:
409:
398:
392:
386:
381:Voice object
380:
370:
364:
358:
354:
349:
338:
334:
328:
324:
322:
311:
305:
299:
293:
287:
281:
275:
270:
266:Windows 2000
262:Visual Basic
247:
239:
223:
207:
196:
190:
184:
174:
168:
162:
156:
150:
140:
131:
126:
123:
118:
112:
107:
103:
100:applications
99:
97:
88:
84:
76:
31:
27:
25:
2397:Gunnar Fant
2375:Researchers
2373:Developers/
2313:Dr. Sbaitso
2121:Readspeaker
2000:Gnopernicus
1896:DirectWrite
1804:EFx Factory
1761:Silverlight
1539:Shadow Copy
1338:Data access
1243:DirectInput
1185:DirectSound
1180:DirectMusic
1129:Silverlight
900:Window-Eyes
483:Windows SDK
359:sapisvr.exe
117:component (
102:and speech
2488:Categories
2338:Voice font
2303:AOLbyPhone
2202:PPG Phonem
2192:Chipspeech
2131:CoolSpeech
1706:Crypto API
1524:PowerShell
1502:management
1465:DirectPlay
1406:Networking
1329:TypeScript
1248:DirectShow
1214:Multimedia
1200:Speech API
1119:GDI / GDI+
1011:2006-04-12
963:2011-11-09
942:References
894:CoolSpeech
642:See also:
609:Windows XP
517:JavaScript
434:Windows XP
341:Windows 98
288:Voice Talk
226:Windows 95
127:event sink
2347:Protocols
2333:PlainTalk
2177:Alter/Ego
2156:LaLaVoice
2151:Voiceroid
2045:eCantorix
2005:Gnuspeech
1926:Uniscribe
1607:Libraries
1554:Event Log
855:and later
807:and later
801:and later
579:includes
543:Windows 7
40:Microsoft
2364:VoiceXML
2308:DialogOS
2227:Vocaloid
2222:Vocalina
2207:Realivox
2141:CereProc
2101:Talk It!
2079:Speaking
2071:software
1995:eSpeakNG
1984:Speaking
1852:Remoting
1756:Remoting
1699:Security
1309:VBScript
1109:Direct3D
1104:Direct2D
969:Archived
919:See also
537:SAPI 5.4
469:SAPI 5.3
448:SAPI 5.2
420:SAPI 5.1
406:SAPI 5.0
329:SAPI 5.0
204:Versions
119:sapi.dll
2431:Process
2252:Echo II
2245:Machine
2232:Xiaoice
2170:Singing
2091:DECtalk
2038:Singing
2024:FreeTTS
1889:support
1751:ADO.NET
1746:ASP.NET
1711:CAPICOM
1587:ActiveX
1450:P2P API
1413:Winsock
1355:ADO.NET
1304:JScript
1221:DirectX
1205:XAudio2
565:L&H
523:string.
510:(ABNF).
426:JScript
258:ActiveX
115:runtime
104:engines
52:Windows
50:within
2448:Currah
2422:Yamaha
2318:MBROLA
2267:Phasor
2182:Cantor
1991:eSpeak
1460:MS MPI
1365:OLE DB
1294:MSHTML
1238:Xinput
793:SAPI 4
755:up to
703:SAPI 5
684:later.
619:, and
428:, and
345:NT 4.0
244:SAPI 4
236:SAPI 3
220:SAPI 1
34:is an
2458:PSOLA
2359:SABLE
2287:TuVox
2161:15.ai
2136:IVONA
2055:Sinsy
2019:Flite
1842:MSRPC
1392:MSXML
1173:Audio
1134:WinUI
935:SASDK
143:- in
2272:RIAS
2217:UTAU
2010:Orca
1738:.NET
1675:NDIS
1670:WDDM
1663:UMDF
1658:KMDF
1582:COM+
1455:MSMQ
1445:BITS
1435:NDIS
1360:ODBC
1195:XACT
1164:WinG
906:JAWS
757:2022
753:2008
573:Mary
571:and
569:Mike
496:The
462:SSML
460:and
458:SRGS
343:and
323:The
228:and
145:MIDL
70:and
46:and
32:SAPI
26:The
1857:WCF
1834:IPC
1824:CSF
1819:CCF
1781:WPF
1776:WCS
1771:WCF
1766:TPL
1690:VxD
1685:BDA
1680:UAA
1653:WDF
1648:WDM
1577:COM
1491:WCF
1418:LSP
1397:OPC
1350:ADO
1319:XDR
1314:BHO
1287:Web
1268:XNA
1124:WPF
851:in
657:GUI
623:.
375:XML
254:C++
250:COM
56:SDK
36:API
30:or
2490::
1786:WF
991:^
615:,
611:,
599:A
591:.
575:.
545:.
444:.
436:.
268:.
74:.
66:,
60:OS
2017:/
1993:/
1960:e
1953:t
1946:v
1077:e
1070:t
1063:v
1014:.
966:.
199:.
187:.
23:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.