I'm building Voxmint, a text-to-speech tool that started because AI voices kept getting Vietnamese tones wrong. It now has 113 voices in 24 languages, with regional accents like Hanoi, Saigon and Hu , Cantonese and Taiwan Mandarin.
If you make voice-overs, courses or videos in a language other than English: which language or accent do current tools still get wrong? Mispronounced names, wrong tones, a "news anchor" voice when you wanted a casual one?
Send me a short line in your language and I'll reply with how Voxmint reads it, and be honest if it's not good enough yet.
Text to speech with 113 natural voices in 24 languages. Hanoi and Saigon Vietnamese, Mandarin and Cantonese, Brazilian and European Portuguese. Or describe a voice in a sentence and save it; a fixed seed brings the same voice back in every project. Add [laughing] or [whispering] inline. Batch up to 100 lines, word timings for captions, and a REST API on the same credits. No voice cloning, by design.
