CONTEXT
Create an exclusive and unique voice, based on the voices of real women, for Avon's virtual assistant - Angela. In this way, she aims to be the voice of Brazilian women to fight for more equality, more rights and more spaces, wherever they want.
Solution
We developed a landing page to publicize the campaign and invite women to donate their voices, storing the donated audios for future deep voice/machine learning training. All entries were evaluated and qualified, and the best audios were selected for the training process, in this project created in partnership with Wunderman Thompson and Evil Twin.
Based on the donated voices and using an open dataset, we began the construction of the deep voice. This process was divided into 3 stages: with 30 hours of pre-training to arrive at a unique voice profile, construction of a base voice that is minimally neutral in relation to timbre and intonation, and finally training of approximately 300 hours for the final result.
After completing the training, we built a dashboard with the voice generation engine, which reads any text input to transform it into Ângela's original and unique voice. Based on the principle of text-to-speech (TTS), we created an exclusive brand voice for Avon.
