GUIDE

An alternative to MeloTTS and OpenVoice in 31 languages

MeloTTS and OpenVoice, both from MyShell and MIT-licensed, are a popular pair: MeloTTS speaks fast enough for real time on a processor, and OpenVoice copies the tone of a reference clip onto its speech. Together they cover six languages, and both repositories were last updated in 2024 and 2025.

The free SuperClonica engine also runs on an ordinary processor, speaks 31 languages and comes with a catalog of ready voices. This guide compares them honestly and says when MeloTTS or OpenVoice is the better pick.

MeloTTS and OpenVoice in short

For Chinese, regional English accents or instant tone copying, the pair is a solid open choice.

  • MeloTTS: English with American, British, Indian and Australian accents, Spanish, French, Chinese mixed with English, Japanese and Korean.
  • MeloTTS is fast enough for real-time speech on a processor.
  • OpenVoice V2 copies the tone color of a reference clip at generation time and natively supports English, Spanish, French, Chinese, Japanese and Korean.
  • Both are under the MIT license.

Compare the sound free

On the page of any voice, paste a line you voiced with MeloTTS or OpenVoice, 30 to 100 characters, choose the language and press Voice it. In a few seconds you can compare, with no account.

What SuperClonica does differently

It runs on an ordinary processor too: in our tests a short phrase took 0.43 s on four threads of a Ryzen 7 5800X.

  • 31 languages, including German, Russian, Portuguese, Italian, Polish, Dutch, Turkish, Hindi and Arabic; Chinese is not among them.
  • Ready voices: ten stock voices and more than 170 catalog voices with free demos.
  • Each voice is a JSON file of about 0.3 MB and speaks every language of the model.
  • One command to install: python -m pip install superclonica-cpu, or a Docker image with an HTTP API.

Copying a tone or training a voice

OpenVoice adds a reference tone to every generation. In SuperClonica, a voice is trained once in the studio from a clean 5 to 10 second recording, on a computer with an NVIDIA graphics card, or ordered on the exchange from an author who trains it. After that it runs on any processor and in all 31 languages, with a trace of the accent of the original recording. Clone only voices whose owners agreed.

Which one to choose

Choose MeloTTS for Chinese mixed with English or for a choice of English accents, and OpenVoice when you need to copy a tone from a clip right away. Choose SuperClonica for German, Russian, Portuguese, Italian and the other languages the pair does not speak, for ready character and narrator voices, and for one simple install for speech and voices.