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?
Polish synthesis is demanding because of dense consonant clusters (words like "bezwzględny" or "źdźbło" string together sounds that trip up naïve grapheme-to-phoneme rules) and a rich set of sibilants — the engine must distinguish the soft ś/ź/ć from the hard sz/ż/cz and the retroflex-leaning rz. Stress is highly regular, falling on the penultimate syllable, which actually helps prosody, but the nasal vowels ą and ę shift pronunciation depending on the following consonant. Polish TTS is widely used for navigation apps, public-transport announcements and e-commerce in one of Central Europe's largest markets.
Ekzemplo — Polski
“W Szczebrzeszynie chrząszcz brzmi w trzcinie, a mieszkańcy spokojnie piją kawę na rynku.”
Nacia nomo
Polski
Parolantoj
~40 million native speakers
Lingva familio
Indo-European (West Slavic)
Skripto
Latin script with diacritics
Parolita en
Poland, with large communities in the UK, Germany, the US and Canada
Public transport and railway announcements in Polish cities
GPS and navigation voice guidance for Polish drivers
E-commerce product readouts and order confirmations
Corporate e-learning and onboarding narration
Accessibility tools and screen readers for Polish users
Polish Teksto al Parolo - FAQ
Yes — clusters like "szcz", "drz" and "źdźbło" are modeled at the phoneme level, so tongue-twisters and ordinary dense Polish words are pronounced cleanly rather than syllable by syllable.
It separates the soft series (ś, ź, ć, dź) from the hard series (sz, ż, cz, dż) and the rz sound, which is essential because confusing them changes word meaning in Polish.
Polish stress reliably falls on the second-to-last syllable, and our prosody model follows that rule, with the standard exceptions for certain borrowed and grammatical forms.
Yes. Their realization is context-dependent — denasalizing or splitting into a vowel-plus-nasal before stops — and the engine applies the appropriate variant based on the following sound.
