Voice cloning creates a digital copy of a voice. Unlike other tools that upload your recordings to servers, this tool runs two AI models directly in your browser: MeloTTS generates natural speech from text, and OpenVoice transfers the tone color of your reference voice onto the result.
How to use: type or paste your text, optionally upload or record a 10-second voice sample, and click Generate. Without a reference sample the tool speaks with its built-in AI voice; with one, the output adopts your reference voice's timbre.
Yes, completely free with no limits. All processing runs in your browser — there is no server cost to pass on.
No. Your reference audio and generated audio never leave your device. The AI models run locally in your browser via WebAssembly.
A short sentence typically takes 1-3 seconds after the models are loaded. The first visit downloads the AI models, which takes a few minutes on a fast connection.
Chinese and English, including mixed sentences. Other languages are not yet supported by the browser models.
Only clone voices you have the rights to — your own voice or voices you have permission to use. Never use cloned voices to impersonate others or for fraud.