In the world of audio production, voice has always been the most stubborn element. You can pitch a snare drum, time-stretch a synth pad, or reverse a cymbal with impunity. But the human voice? It resists manipulation. Stretch it too far, and it becomes a gargling demon. Pitch it up, and you get chipmunks. For decades, dialogue editing has remained a surgical, painstaking craft—cutting breaths, aligning syllables, masking mouth clicks.
Until now.
Outstanding. A paradigm shift for dialogue editing. Disclosure: Expansion Labs provided a review license for the EVE Studio tier. No other compensation was received. The author has no financial interest in the company. expansion voice editor
One beta tester, a dialogue supervisor for an animated series, used this to create three distinct monster voices from a single actor’s performance—without re-recording. Need to replace the word “sad” with “mad” in a finished take? In Pro Tools, you’d pray for an alternate take. In EVE, you type the new word into a text field. The editor analyzes the surrounding prosody and synthesizes the missing phonemes from the actor’s own voice model, built live from the session. The result is indistinguishable from a real recording. It’s not text-to-speech; it’s speech-to-speech recomposition. In the world of audio production, voice has