Comparison of speech synthesizers
{{short description|None}}
Here is a non-exhaustive comparison of speech synthesis programs:
General
class="wikitable sortable" style="font-size: 85%; text-align: center; width: 100%;" |
style="width:12em" | Name
! Creator(s) ! First public release date ! Latest stable version |
---|
style="text-align:left;" | 15.ai
| 15 | 2020 | 2022 | |
style="text-align:left;" | Apple PlainTalk
| 1984 | 2018 | Bundled with Mac OS X |
style="text-align:left;" | AT&T Natural Voices
| {{dunno}} | 2008 |
style="text-align:left;" | Polly
|Amazon AWS |2016 |2019 |
style="text-align:left;" | Cepstral
| Cepstral | 2000 | 2013 |
style="text-align:left;" | CereProc
| CereProc | 2006 | 2017, February |
style="text-align:left;" | eSpeak
| Jonathan Duddington | 2006, February 10 | 2022, April 3 | GPLv3+ |
style="text-align:left;" | Festival Speech Synthesis System
| CSTR | {{dunno}} | 2014, December |
style="text-align:left;" | FreeTTS
| Paul Lamere | 2001, December 14 | 2009, March 9 | BSD |
style="text-align:left;" | LumenVox
| LumenVox | 2011 | 2019 |
style="text-align:left;" | Microsoft Speech API
|1995 |2012 |Bundled with Windows |
style="text-align:left;" | VoiceText
| ReadSpeaker (Formerly Neospeech) | 2002 | 2017 |
style="text-align:left;" | Nuance Vocalizer
| Nuance Communications, Inc. | {{dunno}} | 2018 |
Technical voice details
class="wikitable sortable" style="font-size: 85%; text-align: center; width: 100%;" |
Platform
! SSML ! WS ! PLS ! CLI |
---|
style="text-align:left;" | 15.ai
| {{dunno}} | {{dunno}} | {{dunno}} | {{dunno}} | {{dunno}} |
style="text-align:left;" | Apple PlainTalk
| {{dunno}} | {{dunno}} | {{dunno}} | {{dunno}} | {{dunno}} |
style="text-align:left;" | AT&T Natural Voices
| {{Yes}} |5.1 | {{dunno}} | {{dunno}} | {{dunno}} |
style="text-align:left;" | Cepstral (company)
| {{Yes}} |5.x | {{Yes}} | {{Yes}} | {{Yes}} |
style="text-align:left;" | CereProc
| {{Yes}} |5.x | {{Yes}} | {{Yes}} | {{Yes}} |
style="text-align:left;" | eSpeak
| {{Yes}} |5.x | {{dunno}} | {{dunno}} | {{Yes}} |
style="text-align:left;" | Festival Speech Synthesis System
| {{dunno}} | {{dunno}} | {{dunno}} | {{dunno}} | {{Yes}} |
style="text-align:left;" | FreeTTS
| {{dunno}} | {{dunno}} | {{dunno}} | {{dunno}} | {{dunno}} |
style="text-align:left;" | LumenVox
| {{Yes}} |5.x | {{Yes}} | {{Yes}} | {{Yes}} |
style="text-align:left;" | Microsoft Speech API
| {{partial|5.x only|align=|style=|color=}} |4.x/5.x | {{dunno}} | {{dunno}} | {{dunno}} |
style="text-align:left;" | Nuance Vocalizer
| {{dunno}} | {{dunno}} | {{dunno}} | {{dunno}} | {{dunno}} |
style="text-align:left;" | VoiceText
| {{Yes}} |5.x | {{dunno}} | {{dunno}} | {{dunno}} |
Technical details
class="wikitable sortable" style="font-size: 85%; text-align: center; width: 100%;" |
style="width:12em" | Name
! Online demo ! Available language(s) ! Available voices ! Programming language |
---|
style="text-align:left;" | 15.ai
| {{yes}} | English (United States) | 50+ | Python | Any |
style="text-align:left;" | Apple PlainTalk
| {{dunno}} | English (United States), ... | 15+ | {{dunno}} |
style="text-align:left;" | AT&T Natural Voices
| {{yes}} | English (British), English (Indian), English (US), French, French (Canadian), German, Italian, Spanish (Latin American) | 20 | C++ |
style="text-align:left;" | Cepstral
| {{yes}} | English (British), English (US), Italian, French (Canadian), German, Spanish (American), ... | 25+ | C/C++ | Mac OS X |
style="text-align:left;" | CereProc
| {{yes}} | English (British), English (US), English (Scottish), English (Irish), French, French (Canadian), German, Austrian German, Italian, Irish, Spanish (Castilian), Spanish (Latin American), Dutch, Polish, Portuguese, Portuguese (Brazilian), Japanese, Catalan, Scottish Gaelic, Swedish, Russian, Mandarin | 46 | Java / C C++ / Objective C / Python / C# & .Net through SAPI |
style="text-align:left;" | eSpeak
| Samples | Afrikaans, Albanian, Armenian, Cantonese, Catalan, Croatian, Czech, Danish, Dutch, English (British, US, Scottish, Westindies...), Esperanto, Estonian, Finnish, French (France, Belgium), Georgian, German, Greek, Hindi, Hungarian, Icelandic, Indonesian, Italian, Kannada, Kurdish, Latvian, Lojban, Macedonian, Malayalam, Mandarin, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Spanish, Swahili, Swedish, Tamil, Turkish, Vietnamese, Welsh. | several | C++ |
style="text-align:left;" | Festival Speech Synthesis System
| {{yes}} | English (UK), English (US), Spanish, Hindi, Croatian, Finnish, Polish, Welsh. | Several | C++ |
style="text-align:left;" | FreeTTS
| {{dunno}} | English... | Several | Java |
style="text-align:left;" | LumenVox
| {{yes}} | Danish, Dutch, English (Australian), English (US), English (UK), English (Welsh), English (Indian), French, French (Canadian), German, Icelandic, Italian, Polish, Portuguese, Portuguese (Brazilian), Romanian, Russian, Spanish (North American), Spanish (Latin American), Spanish (Castilian), Swedish, Turkish, Welsh, Welsh English | 57 |
style="text-align:left;" | Nuance Vocalizer
| {{yes}} | US English, Australian English, Indian English, Irish English, South African English, UK English, Argentinian Spanish, Castilian Spanish, Colombian Spanish, Mexican Spanish, Arabic, Catalan, Basque, Galician, Dutch, Belgian Dutch, Portuguese, Brazilian Portuguese, Bulgarian, French, Canadian French, Cantonese (Hong Kong), Mandarin, Mandarin Taiwanese, Czech, Danish, Finnish, German, Greek, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Norwegian, Polish, Romanian, Russian, Slovak, Swedish, Thai, Turkish | 70+ | C/C++ |
style="text-align:left;" | VoiceText
| {{yes}} | English (US), English (British), American Spanish, Canadian French, Chinese Mandarin, Japanese, Korean | 13 |