Created initially as a Word Press plugin in 2008, Speeka also supports conversion of generic html pages to MP3.
Once a page is registered with the system, Speeka’s crawler regularly checks the page content for changes. Speeka’s capacity is reduced these days. Though able to serve existing users without issues, it’s just running from a single dedicated server now largely for closed project use only.
I’ve left this page up as there aren’t many places where you can compare the various open source speech engines.
There are now several commercial alternatives available which are simple to implement for web – eg Voice Forge, ReadSpeaker, BrowseAloud, ROK Talk and more than a few plugins for WordPress have emerged.
For developers The Web Speech API is being widely adopted by browsers and provides efficient text-to-speech with relative ease.
Text-to-Speech Demos
To quickly compare voices use the pre-rendered clips beneath the form.
Use the following to test the supported voices and parsing – text or html input is acceptable. Optional post processing through Sox can improve some of the harsher voices.
Input is annotated basically by default – headings are noted and acronyms and abbreviations are expanded. Additional elements such as forms, lists, addresses, tables and links are announced if the semantic annotation checkbox is ticked. Forms and tables are not reliably processed, their presence is noted to the listener but content is simply linearised.
The audio’s ID3 content is constructed from page title, the encoded text content and user name.
Pre-rendered Voices for Quick Comparison
| Young British Male – Mbrola EN1 voice_en1.mp3
|
| Old British Male – CSTR ‘rab’ diphone voice_rab.mp3
|
| Scottish/UK Male – CMU ‘awb’ arctic hts voice_awb.mp3
|
| Scottish/UK Male – Nitech ‘awb’ arctic hts voice_awb2.mp3
|
| Scottish/US Male – CSTR ‘ked’ diphone voice_ked.mp3
|
| Thoughtful US Female – CMU ‘clb’ arctic cg voice_clb.mp3
|
| Thoughtful US Female – Nitech ‘clb’ arctic hts voice_clb2.mp3
|
| Bored US Female – Mbrola US1 voice_us1.mp3
|
| Curious US Female – CMU ‘slt’ arctic cg voice_slt.mp3
|
| Curious US Female – Nitech ‘slt’ arctic hts voice_slt2.mp3
|
| Bored US Male – Mbrola US2 voice_us2.mp3
|
| Smooth US Male – Mbrola US3 voice_us3.mp3
|
| Lazy US Male – CSTR ‘kal’ diphone voice_kal.mp3
|
| Chilled US/Canadian Male – CMU ‘jmk’ arctic cg voice_jmk.mp3
|
| Chilled US/Canadian Male – Nitech ‘jmk’ arctic hts voice_jmk2.mp3
|
| Narrator US Male – CMU ‘rms’ arctic cg voice_rms.mp3
|
| Narrator US Male – Nitech ‘rms’ arctic hts voice_rms2.mp3
|
| Precise US Male – CMU ‘bdl’ arctic cg voice_bdl.mp3
|
| Precise US Male – Nitech ‘bdl’ arctic hts voice_bdl2.mp3
|
| Lancashire Male – eSpeak en-n voice_en-n.mp3
|
| Standard English Male – eSpeak en voice_en-def.mp3
|
| RP Male – eSpeak en-rp voice_en-rp.mp3
|
| Brummie Male – eSpeak en-wm voice_en-wm.mp3
|
| West Indian Male – eSpeak en-wi voice_en-wi.mp3
|
| Scottish Male – eSpeak en-sc voice_en-sc.mp3
|
| US Male – eSpeak en-us voice_en-us.mp3
|
| Esperanto – eSpeak eo voice_eo.mp3
|
| French – eSpeak fr voice_fr.mp3
|
| German – eSpeak de voice_de.mp3
|
| Russian – eSpeak ru voice_ru.mp3
|
| Polish – eSpeak pl voice_pl.mp3
|
| Italian – eSpeak it voice_it.mp3
|
| Spanish – eSpeak es voice_es.mp3
|
| Latin – eSpeak la voice_la.mp3
|
| Commercial Voices for Contrast |
|---|
| British Male – Cepstral Lawrence voice_Lawrence.mp3
|
| British Female – Cepstral Millie voice_Millie.mp3
|
| US Male – Cepstral David voice_David.mp3
|
| British Male 2 – Loquendo Simon voice_LoqSi.mp3
|
| British Female 2 – Loquendo Kate voice_LoqKa.mp3
|
| US Male 1 – Microsoft Sam voice_MSSam.mp3
|
| US Male 2 – Microsoft Mike voice_MSMike.mp3
|
| US Female – Microsoft Mary voice_MSMary.mp3
|