GUIDE

RPG Maker voice acting with AI voices

Voiced dialogue makes an RPG Maker game feel bigger, but hiring actors for hundreds of lines is out of reach for most solo developers. Text to speech fills the gap: every line gets a voice the day it is written, for a demo, for placeholder dialogue, or for the finished game.

The free SuperClonica engine voices text offline on an ordinary processor and writes OGG files, the format RPG Maker uses for audio. This guide shows how to voice a whole script at once, how to play the lines in events, and which voices you can ship in a released game.

Browse voices Install the SuperClonica engine

How voiced dialogue works in RPG Maker

Basic voiced dialogue needs no plugin; voice plugins only automate the Play SE step.

  • A project keeps its sounds in the audio folder: bgm, bgs, me and se. Voice clips usually go into audio/se.
  • In an event, put the Play SE command right before Show Text, and the line starts with its message box.
  • RPG Maker MV and MZ use OGG files; many asset packs also include M4A copies for some platforms.
  • The engine speaks 31 languages, Japanese included; Chinese is not supported yet.

Pick voices free online

On the page of any voice, type a line of your character, 30 to 100 characters, choose the language and press Voice it. In a few seconds you hear whether the voice fits the hero, the villain or the shopkeeper, with no account.

Voice the whole script

The same text, voice and seed always give the same audio, so you can regenerate only the lines that changed.

  • Install the engine: python -m pip install superclonica-cpu.
  • Keep the dialogue in a lines.csv table with the columns file, voice and text, for example Hero_001, M2, We leave for the castle at dawn.
  • A short Python script reads it with tts = Superclonica() and csv.DictReader(open('lines.csv', encoding='utf-8')), then for each row runs audio, rate = tts.synthesize(row['text'], row['voice'], 'en', seed=1) and tts.save('audio/se/' + row['file'] + '.ogg', audio).
  • Refresh the sound list in the editor, and the new clips appear in Play SE.

Make the dialogue sound natural

Keep one voice per character and write lines the way people speak: short sentences, a full stop where a breath belongs. Write numbers as words, “fifty gold” rather than “50 gold”, because digits are read as plain numbers. Leave Pitch at 100 in Play SE: in RPG Maker it changes speed as well, so choose another voice instead. Volume and Pan are safe to adjust.

Voices you can ship

For a demo or a jam game, any catalog voice is fine. For a released game, use a voice you have the rights to: the ten stock voices of the model, M1 to M5 and F1 to F5, or your own voice trained in the SuperClonica studio from a clean 5 to 10 second recording of an actor who agreed, on a computer with an NVIDIA graphics card, or a custom voice ordered on the exchange. Fan-made character voices are for parody and fan games, not for commercial ones.