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?
Japanese text-to-speech is governed by pitch accent rather than stress: each word has a fixed high-low pitch pattern, and getting it wrong makes a voice sound foreign even when every syllable is correct — for instance "hashi" can mean bridge or chopsticks depending on the accent. The writing system mixes Kanji, Hiragana and Katakana with no spaces, so the engine must segment text and pick the right reading for Kanji that have several (端 vs 橋 vs 箸). Standard (Tokyo) accent is the default for most synthesis, while regional varieties such as Kansai have a different pitch pattern entirely.
Ekzemplo — 日本語
“今日はとても良い天気なので、みんなで公園へ散歩に出かけて、美味しいお弁当を食べましょう。”
Nacia nomo
日本語
Parolantoj
about 125 million speakers, almost entirely in Japan
Lingva familio
Japonic (generally treated as a language isolate at family level)
Skripto
Mixed Kanji, Hiragana and Katakana
Parolita en
Japan, with small communities in Brazil, Hawaii and immigrant populations
The engine predicts each word's high-low pitch pattern in context, which is what distinguishes pairs like 橋 (hashi, bridge) from 箸 (hashi, chopsticks) and makes the voice sound natural.
Yes. It segments unspaced Japanese text, converts Kanji to the correct reading and handles Katakana loanwords and Hiragana grammar together.
Mostly yes. Readings such as 生 (sei, nama, i-) or names are chosen from context, though uncommon proper nouns can occasionally be ambiguous.
Voices use Standard (Tokyo) pitch accent, which is the norm for narration, announcements and most media; full Kansai-accent synthesis is a different dialect pattern.
