Adobe VoCo Lets You Edit Speech As Easily As Text
Adobe VoCo, dubbed Photoshop for audio, ingests speech, deconstructs it, then creates new words
Adobe demonstrated audio tech that lets you edit recorded speech, you can alter what the recorded person said, or create an entirely new sentence using their voice. It seems inevitable that it has been dubbed “photoshop for audio.”
The tech, VoCo (voice conversion), presents the user with a text box. Initially the text box shows the spoken content of the audio clip. You can then move the words around, delete fragments, or type in new words. When you type in a new word, there’s a small pause while the word is constructed—then you can press play and listen to the new clip.
VoCo works by ingesting a large amount of voice data (about 20 minutes right now, but that’ll be improved), breaking it down into phonemes (each of the distinct sounds that make up a spoken language), and then attempting to create a voice model of the speaker, but Adobe hasn’t provided much detail yet.
When you edit someone’s speech, VoCo either finds that word somewhere within the 20-minute clip—or if the word hasn’t been uttered, it is constructed out of raw phonemes. At around the 4:30 mark in the video you can hear the phase “three times” being constructed from scratch; if you listen carefully, it does sound a bit synthetic, but it’s not awful. Copying and pasting existing words sounds better.
With VoCo, Adobe is also being conscientious: even though it’s just beta technology, the company is already talking about “watermarking and detection” to prevent fraudulent use.
VoCo was demonstrated at Adobe Max 2016, where the company usually shows off new tech. If VoCo does make it out of the beta stage, it would probably be added to Adobe Audition, where you could use it to edit podcasts and voiceovers.