Upload or record 3-20 seconds of audio, trim it, then save it as a reusable voice clone.
Drop a file, paste a URL, or record directly from your microphone.
Download audio from a direct link or YouTube video.
Record a fresh sample with live input level monitoring.
Assign a unique ID, language, and gender — e.g. EN_F_Anna.
The spoken text that matches this audio — type it or auto-transcribe.
Play back the trimmed audio before saving to the library.
No audio loaded yet. Load a file above (Step 1) or use Voice Design below.
Write the cloned voice to your active voices folder.