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?
Indonesian is one of the friendliest languages in the world for speech synthesis, and the reasons are structural. Its Latin spelling is close to fully phonemic, it has no lexical tone, no grammatical gender, and no verb conjugation for tense or person, so a model is spared most of the ambiguity that makes other languages hard to read aloud. What it does demand is fluent handling of affixation: prefixes and suffixes such as me-, pe-, -kan, and -i stack onto roots to build long derived words that must be spoken as single units rather than assembled fragments. Standardised from Malay at independence and deliberately designed to unite a nation of hundreds of local languages, Bahasa Indonesia is the shared second language of a vast, overwhelmingly mobile-first audience, which is why voice interfaces, edtech, and audio content in Indonesian scale so quickly.
Ekzemplo — Bahasa Indonesia
“Teknologi pengubah teks menjadi suara membantu pelajar dan profesional mendengarkan tulisan mereka dengan mudah.”
Nacia nomo
Bahasa Indonesia
Parolantoj
Around 270 million speakers, mostly as a second language, across the world’s fourth most populous country
Lingva familio
Austronesian (Malayic)
Skripto
Latin
Parolita en
Indonesia, with close mutual intelligibility with Malay as spoken in Malaysia, Brunei, and Singapore
E-learning and edtech narration for a mobile-first student population
E-commerce and fintech voice prompts and IVR
News, podcast, and social-media voiceovers
Audiobooks and long-form content narration
Accessibility and screen-reader style audio for public services
Indonesian Teksto al Parolo - FAQ
Unusually so. Spelling maps to sound predictably, there is no tone to track, and stress is regular enough that the model rarely has to guess. Most remaining difficulty comes from foreign loanwords and English brand names embedded in Indonesian text.
Indonesian and Malay are closely related and share much of their vocabulary, so an Indonesian voice is often intelligible to Malay speakers. Pronunciation and some everyday word choices differ, though, so for a Malaysian audience the result will sound noticeably Indonesian rather than native.
Indonesian builds meaning by attaching affixes to a root, producing long derived forms such as mempertanggungjawabkan. The voice reads these as single fluent words, preserving natural rhythm instead of breaking them into pieces.
Not with the voice available today. The Indonesian voice on TTS.ai was trained on, or fine-tuned from, recordings licensed for non-commercial use, so it is marked "Personal and non-commercial use only" and is not covered by the commercial license on paid plans.
