Voicemy

Voicemy is an AI platform for creating voice content, including voice cloning and text-to-speech audio generation. It works best in English, though you can try other languages (including Russian).

Training voice models

You can train a custom model to generate audio in a specific voice. Upload an audio sample, and the system analyzes it and attempts to replicate the voice. The interface is in English; training tools are available under Training (Train voice and Upload model).

You can also use ready-made models shared by the community. Popular options are collected in Community (List of models).

Voice cloning and text-to-speech

Voicemy can clone voices, including celebrity-style voices available in its library. Search helps you find a specific character without scrolling through the full list.

For text-to-speech, you can enter text in any language, but English is typically easier for the models. The free tier includes 250 characters per audio clip.

Key features

• Basic Voicemy features are available for free
• Create unique audio recordings
• Clone a celebrity voice or your own
• Train models on your own source data
• Small audio generations typically take about a minute