Talkapella is based on a sophisticated speech-to-music technology that builds on the concept of AutoTune. A user’s speech is intelligently mapped to four voices to create a rich vocal harmony. Just like a real composer, the artificial intelligence maps the speech patterns to the musical patterns, so the words match the phrase of the melody. This is done by intelligently stretching and compressing the speech based on the location of vowels and consonants. The result is a magical transformation of speech into a killer a cappella track.
According to Prerna Gupta, founder and CEO, Khush:
“LaDiDa and Songify have been downloaded more than 7 million times, and Khush is profitable on a minimal amount of funding — this is clear evidence that there’s a market for apps that help people express themselves with music. Our goal is to make music self-expression as ubiquitous as social expression. User demand for an a cappella version of Songify has been enormous, and we’re thrilled to bring Talkapella to market.”
Take a look: