Etikedoj kiujn la elektita modelo komprenas - klaku por meti unu en vian tekston kie ĝi okazas:
This model reads plain text, so inline tags are ignored. For tag-based emotion, switch to an expressive model like Orpheus or Bark.
Natural- language delivery hints. Honored by Qwen3- TTS today; other expression models coming soon.
Tiu modelo ne subtenas stilajn instrukciojn — ŝanĝu al modelo kiu subtenas ilin (ekz. Qwen3-TTS).
Difini proprajn elparolojn (vorto = elparolo):
-12
+12
Kontrolas esprimpovon (0 = neŭtrala, 1 = tre esprima)
Klasigilo- libera gvidpezo (pli alta = pli prompt- sekvanta)
Priskribi la voĉstilon en natura lingvo (Parler uzas tion anstataŭ antaŭdifinitaj voĉoj)
Dia dialoga formato: Uzu [S1] kaj [S2] por marki malsamajn parolantojn. Ekzemplo: [S1] Saluton! [S2] Saluton, kiel vi fartas?
Turkish is an agglutinative language: a single root can take a long chain of suffixes ("evlerinizden" = "from your houses"), so a TTS engine has to handle very long, rarely-seen word forms gracefully rather than relying on a dictionary of whole words. Vowel harmony governs which vowels appear in those suffixes, and the alphabet's special letters — the dotless ı versus dotted i, plus ç, ş, ğ, ö, ü — must be read precisely, with the soft ğ lengthening the preceding vowel rather than being voiced. Word stress usually falls on the final syllable, and Turkish voices are popular for navigation, news readout and e-commerce serving Turkey and its European diaspora.
Ekzemplo — Türkçe
“Bugün hava çok güzel, hadi Boğaz kenarında yürüyüş yapıp bir bardak Türk çayı içelim.”
Nacia nomo
Türkçe
Parolantoj
~80 million native speakers
Lingva familio
Turkic (Oghuz branch)
Skripto
Latin script (since 1928) with diacritics
Parolita en
Turkey and Cyprus, with large communities in Germany, the Netherlands and Austria
GPS navigation and traffic guidance for Turkish drivers
News and article readout for Turkish media apps
E-commerce and order-status prompts for Turkish online stores
IVR and call-center systems for banks in Turkey
Accessibility narration for the Turkish-speaking diaspora in Germany
Turkish Teksto al Parolo - FAQ
It treats ı and i as the separate vowels they are in Turkish, with distinct pronunciations — confusing the two would mispronounce a large share of common words, so the engine keeps them apart.
Yes. Because Turkish builds words by stacking suffixes onto a root, our synthesis works at the morpheme and phoneme level, so long unfamiliar forms like "evlerinizden" are voiced correctly without a whole-word dictionary entry.
The yumuşak ge (ğ) is rendered as a lengthening of the preceding vowel rather than a hard consonant, matching standard Istanbul Turkish pronunciation.
Vowel harmony is inherent in correctly spelled input, which the engine reads faithfully, and its prosody model places stress on the final syllable by default, with the usual exceptions for place names and loanwords.
