Vocal Synth · Instrument

Vocalizer

Type words, draw a melody, make a voice sing them. Free and open source.

Overview

Vocalizer turns typed words into a sung vocal you can drop straight onto a track. Type your text, put a MIDI melody on the channel, hit Generate, and a neural text-to-speech voice is pitch-corrected to follow your notes — formant-preserving (TD-PSOLA), so it stays musical. Audition it in place, then drag the rendered WAV onto any audio track. It's the stylized robot-singer / talkbox / autotune sound rather than a human-vocalist emulator — perfect for hooks, textures, and vocal chops across bass music, hip-hop, and electronic. Because it uses espeak-ng (GPLv3) under the hood, the whole plugin is free and open source, with the full source on GitHub.

Features

• ▸Type text → capture a MIDI melody → Generate → the words sing your melody
• ▸Bundled neural TTS (Piper / ONNX) — offline, consistent, clean voiced output
• ▸Formant-preserving pitch correction (TD-PSOLA)
• ▸Multiple voices; drop more models into ~/Documents/Vocalizer/Voices/
• ▸Drag the rendered WAV straight onto an audio track
• ▸Native Apple Silicon (arm64); full state (incl. melody) persists
• ▸Free & open source — GPLv3, full source on GitHub

Listen