GUIDE

A VOICEVOX alternative for multilingual videos

VOICEVOX is one of the best-loved free text-to-speech programs for Japanese videos, with characters such as Zundamon and Shikoku Metan known far beyond Japan. It is made for Japanese, though, and channels that also publish in English, Spanish or Korean need something else for those versions.

The free SuperClonica engine speaks 31 languages, Japanese included, with the same voice in each of them. This guide compares the two honestly and shows a multilingual workflow.

Browse voices Install the SuperClonica engine

VOICEVOX in short

For Japanese videos it is a superb free tool.

  • Free for commercial and non-commercial use, under the terms of each character.
  • Dozens of characters, such as Zundamon and Shikoku Metan.
  • Detailed intonation editing and a humming feature for singing.
  • Runs on Windows, Mac and Linux; videos must credit VOICEVOX.

Try a voice in another language free

On the page of any voice, type a line of 30 to 100 characters, choose English, Korean or another language and press Voice it. In a few seconds you hear how your channel could sound abroad, with no account.

What SuperClonica adds

Catalog voices were mostly recorded in Russian and keep a slight accent in other languages; listen first, or use the ten stock voices of the model.

  • 31 languages: the same voice speaks Japanese, English, Spanish, Korean, German and more.
  • Narrator voices and game, anime and cartoon characters in the catalog.
  • Your own voice, trained from a recording of a speaker who agreed.
  • An offline engine and an HTTP API for automation.

One voice, many languages

Install the free engine: python -m pip install superclonica-cpu. Voice the English script with superclonica --text-file script_en.txt --voice F2 --lang en --output en.wav, then run the same command with the Korean or Spanish script and --lang ko or --lang es. Every version keeps the same voice, so viewers recognize the channel in any language. The engine runs offline on an ordinary processor, with no character limit.

What VOICEVOX does better

VOICEVOX has a detailed intonation editor, singing and a large cast of free Japanese characters with clear terms. SuperClonica has no intonation editor: rhythm comes from punctuation, and a misread word is fixed by writing it the way it should be read. For Japanese-only videos, VOICEVOX is hard to beat; for the same channel in several languages, SuperClonica fills the gap.