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?
Persian text-to-speech has to reconcile a writing system that omits most short vowels: the Perso-Arabic script normally marks only long vowels, so a synthesizer must infer the missing /a/, /e/, /o/ diacritics from context to pronounce a word correctly. The text also runs right-to-left while embedded Latin numerals and loanwords run left-to-right, forcing the engine to handle bidirectional reordering before phonemization. The ezāfe construction — an unwritten linking vowel that binds nouns to their modifiers — is one of the hardest features to predict and a common source of robotic-sounding Persian audio. Good Persian TTS therefore depends as much on grapheme-to-phoneme modeling and diacritization as on the acoustic voice itself.
Ekzemplo — فارسی
“تبدیل متن به گفتار فارسی به نرمافزار اجازه میدهد نوشتهها را با صدایی طبیعی و روان بخواند.”
Narration for Iranian e-learning and university lecture platforms
Voiceovers for Persian-language YouTube and Aparat content
Accessibility screen reading for low-vision Persian users
IVR and call-center prompts for businesses in Iran and the diaspora
Audio versions of Persian news articles and literary classics
Persian Teksto al Parolo - FAQ
Yes. The engine processes the bidirectional layout of Perso-Arabic script and correctly handles embedded Latin numbers, dates, and loanwords so they are spoken in the right order.
Persian script rarely writes short vowels, so the system uses a grapheme-to-phoneme model that infers the missing /a/, /e/, and /o/ sounds and the ezāfe linker from surrounding context.
The voices are trained on standard Iranian Persian (Western Persian). They remain intelligible for Dari readers, but some Afghan pronunciations and vocabulary will follow the Iranian standard.
Yes. Persian uses many Arabic-derived words written with Arabic letters such as ث, ذ, and ض; the model maps these to their Persian pronunciations rather than their original Arabic phonemes.
