Dutch Umbhalo kuya kumazwi
Jikelezisa Dutch i-text into natural speech with AI voices. 2 izizwi. Imahhala, akukho ubhaliso — zulazula njenge MP3 noma WAV.
Ukufaka umbhalo wakho kumathegi we-SSML ukulawula okucacile:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Amathegi amamodeli akhethiwe aqonda - chofoza ukuwasusa kusihloko sakho lapho kwenzeka khona:
Le modeli ifunda umbhalo ojwayelekile, ngakho amathegi e-inline akhohlwa. Ukwenza umbono osekelwe kumathegi, shintsha kwimodeli ebonisa umbono njenge-Orpheus noma i-Bark.
Chaza ukuchaza okujwayelekile (igama = ukuchaza):
Ngo Dutch umbhalo-ku-ukukhuluma
Dutch text-to-speech must master a set of guttural and diphthong sounds that have no close English equivalent: the hard "g" and "ch" fricatives, and the rolling diphthongs in "ui", "ij", and "eui". The same orthography is shared by two main standards — Netherlands Dutch and Belgian Flemish — which differ noticeably in rhythm and the realization of the "g", so a voice trained on one sounds foreign to the other. Dutch also forms long compound nouns and uses many spelling-rule vowel doublings (aa, ee, oo) that signal length, all of which the engine must parse for correct stress. The frequent assimilation and final-devoicing at word boundaries add a further layer the synthesizer has to model to avoid a clipped, list-like delivery.
Isibonisi — Nederlands
“Met tekst-naar-spraak laat je de computer Nederlandse teksten voorlezen met een natuurlijke, heldere stem.”
- Igama elisemthethweni
- Nederlands
- Abakhuluma
- ~25 million native speakers
- Imindeni Yesilimi
- West Germanic (Indo-European)
- Isikripthi
- Latin
- Ikhuluma ngaphakathi
- Netherlands, Belgium (Flanders), Suriname, Caribbean
