About disabled voices: The Active toggle moves the voice package between active_voices and hidden_voices. Qwen3-TTS should scan only active_voices.

1 Load or record source

Drop an audio / video file here WAV · MP3 · OGG · FLAC · M4A · MP4 · MKV · WEBM or click to browse

Audio or video URL

Record a fresh sample

0:00

Input level - dB

Mic gain 1.00x

Best peaks: -18 to -9 dB, never red.

Read sample

If the microphone is blocked:

Chrome/Brave/Edge: click the lock icon in the address bar → Microphone → Allow, then reload.
Firefox: click the lock icon → remove Blocked → Allow, then reload.
Safari: Settings → Websites → Microphone → allow this site.

Load a file, paste a URL, or record. Then trim, name, and save.

Start

End

Select 3-20 seconds for best cloning.

2 Name and save voice

Language

Gender

Voice ID

My Voices