Voice Clone

Use the local MLX runtime selected by VOICE_CLONE_PROJECT (default: ~/dev/VoiceCloning). It should contain the Qwen3-TTS 1.7B Base 8-bit model, a Python 3.11 environment, saved voice profiles, and clone_voice.py.

Treat source recordings as immutable. Use only reference voices the user supplied or authorized, and do not upload, publish, or send generated speech unless explicitly requested.

This skill includes the repository owner's authorized jin reference profile under assets/voices/jin/. To install it locally, copy that directory to $VOICE_CLONE_PROJECT/voices/jin/. The sample is provided for transparent voice-cloning experiments; do not use it to deceive, impersonate the speaker, imply endorsement, or bypass consent requirements.

Choose the mode

• For speech in an existing cloned voice, use the generation workflow below. If exactly one profile exists and the user does not name one, use it. If several exist and the intended voice is ambiguous, list them and ask which one.
• For a new reference recording, create a reusable profile first. If the user supplied no target text, generate the neutral Korean test sentence 안녕하세요. 이 목소리를 바탕으로 만든 보이스 클로닝 테스트입니다. after preparing the profile.
• Preserve user-provided target text exactly. Default the language to Korean unless the text or request clearly indicates another language.

Generate with a saved profile

List available profiles when needed: