When purchasing a Lite or Pro avatar, we also offer the option to clone your voice. We have prepared a Q&A so that you can learn more about how to do this.
Q: What pricing plan do I need to clone my voice?
A: We offer the ability to do voice cloning of your voice as part of purchasing a Custom Avatar. However, if you plan to buy a custom avatar and are unsure whether your voice will be cloned well, we can clone it before you purchase the avatar, free of charge.
Q: What are the requirements for the recording?
A: Your natural voice, 3-5 minutes of audio, without background noise or other voices. A professional microphone is recommended, but not mandatory.
Q: In which language should I speak for the recording?
A: It’s best to speak in the target language or the one in which you are most fluent.
Q: Is there a specific script that I need to read?
A: No, the content of what you speak is not important.
Q: Where should I send the recording to get a custom voice?
A: Email us at team@spiritme.tech with the audio attached. Please, send it from the email you use for login to Spiritme.
Q: How can I use my voice once it’s created?
A: It will appear in the Studio, available for Multilingual language use.
Q: Can I test the quality of the voice cloning before purchasing an avatar?
A: Yes, send us your sample, and we will add the voice to your account for testing.
Q: In which languages will my voice speak?
A: In the following 29 languages: Arabic, Bulgarian, Chinese, Croatian, Czech, Danish, Dutch, English, Filipino, Finnish, French, German, Greek, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Polish, Portuguese, Romanian, Russian, Slovak, Spanish, Swedish, Tamil, Turkish, Ukrainian.
Q: Can I create two or more custom voices?
A: Yes, email us at team@spiritme.tech to discuss your case.
Q: Do you have an example of cloned voice?
A: We created examples of voice cloning in English, Spanish, French, Italian, German, Polish, and Portuguese. In this folder, you will find the original audio file from which the voice was cloned and an example of how the synthesized voice sounds.