Documentation
A voice for every line.
Loabi TTS turns text into natural, expressive speech — in ދިވެހި and 600+ languages. Here's how to use it.
What it is
A neural text-to-speech studio. Type or paste any text, choose how you want it to sound, and generate clear, human-like audio you can play and download. No setup, no accounts — open the studio and start.
Three ways to make a voice
Instant voice
Type your text and hit generate. A natural voice is picked for you automatically — the fastest way to hear your words.
Pick the traits
Build a voice from selectable traits — gender, age, pitch, accent, and a whisper style. Tap the chips to combine them; only supported combinations are offered, so it always works.
Use your own sample
Upload a short, clean voice sample (3–10 seconds works best) and your text is spoken in that voice. Add a transcript of the sample for a closer match, or leave it blank to have it read automatically.
ދިވެހި — built in
Type in Thaana and the editor switches to right-to-left automatically, rendered in a clean Dhivehi typeface. Numbers and dates are handled for natural pronunciation. Mixed Dhivehi and English in the same line is fine.
Tips for the best results
- · Punctuation shapes delivery — commas and full stops become natural pauses.
- · For cloning, use a quiet sample with one speaker and no background music.
- · Use Fine-tune to adjust speed, or raise quality for longer, more careful reads.
- · Every result can be played, downloaded as a WAV, and reopened from Recent.
How it's made
Loabi TTS is built in collaboration with loabi.dev — bringing modern, natural speech to Dhivehi and beyond. The studio is designed to stay simple: type, choose a voice, and go, with the heavy lifting handled behind the scenes so you never have to think about it.