Workflow Demo
The Workflow
7 steps · click a step number to mark it done
Open Voicebox and have it ready before you start
Download Voicebox from the official site, run the installer, and complete the installation.
Launch Voicebox, go to the Model section, and download the Qwen TTS 1.7B model and the Whisper base transcription model.
Open the Generate tab and click Create Voice to start a new voice profile.
Record a clear 30‑second voice sample (or upload an audio file) and click Transcribe.
Enter a name for your cloned voice and click Create Profile to finalize the voice model.
Switch to the Text‑to‑Speech panel, select the voice you just created, and type the text you want spoken.
Click Generate Speech, wait for synthesis, then export the audio via the three‑dot menu.