Respeecher continues to operate at the intersection of music and technology. Many of our employees have a background in music and relish any opportunity to advance the capabilities of sound through experimentation. That's why our team got excited when composer and trans-media artist, Brigitta Muntendorf, came to us with a collaborative AI singing generator project. With her expertise, the Respeecher team went to work developing a new type of voice synthesis for musicians. But let's start from the beginning.
Creating real-time voice models for a contemporary composer
German-Austrian composer Brigitta Muntendorf creates music by merging different art forms. She seeks experimentation by treating music as a social and aesthetic component of a society that is actively being transformed by digital media.
Brigitta was interested in leveraging synthetic voices for her compositional works. After learning about Respeecher, she came to us looking to find a way to bring her composition to life using a generative AI voice.
To get started, Respeecher would need to create three real-time voice models. The models are trained on three different voices singing in different music genres. Once the models were created, we gave Brigitta full access to them so she could go to work creating her composition using the AI voice generator. She is planning to participate in an upcoming festival to present her work and show off how powerful and beautiful the intersection of music and digital spheres can be.
“Working with Brigitta was fun for us. We got to see how our system copes with some very unusual products of the human vocal tract, such as throat singing. In the end, our best results came from a brand new model only developed in the last couple of weeks before the workshop. It was also great to see the enthusiasm of Birgitta and her colleagues and students at the Hochschule for this new technology. We’re really looking forward to seeing how people will use Respeecher in contemporary music, leveraging the best voice changer capabilities available!”
Grant Reaber, Chief Research Officer at Respeecher.
Voice cloning workshop for music students
After learning more about Respeecher's technology, Brigitta invited our Chief Research Officer, Grant Reaber, to conduct a workshop with the students at the KAMMERMUSIKSAAL HfMT Cologne. The workshop took place on December 5 and centered around voice cloning in music, exploring the innovative possibilities enabled by our AI voice generator.
Grant explained how the technology works and demonstrated different examples of voice conversions. Students could try the technology for themselves and discover the new opportunities it has to offer their work, witnessing firsthand the transformative capabilities of generative AI voice in music composition.
Having experience in providing voice cloning to musicians, the Respeecher team is well-versed in the industry’s nuances, requirements, and limitations. The workshop by Grant Reaber showed how voice AI technology could streamline the creation process and break new ground for musicians.
"It is hard to imagine the potential that cloned vocals can have in the field of music. The workshop with Respeecher was a great experience and inspiration for the students and teachers of the Hochschule für Musik und Tanz Köln, one of the world's foremost performing arts schools and one of the largest music institutions for higher education in Europe. Many thanks to the fantastic team and Grant Reaber!“, commented Brigitta Muntendorf.
The benefits of voice cloning for musicians and composers
Voice cloning, along with the versatility of voice changer software, lets musicians and singers know how their written music will sound. With the emergence of AI singers, it's no longer necessary to go through the process of recording a piece of music and invest all the time, money, and resources that go into that process. And there is no need to hire a team to assist with recording sessions.
Ryan Louder, visual artist, multi-platinum songwriter, and composer from the United Kingdom, has always dreamed of having singers or even an orchestra for the music he writes. His dream came true when he learned about Respeecher's Marketplace, which allows him to sing in a hundred different voices to make his music come alive. With the integration of Respeecher's AI singing generator, Ryan's compositions have reached new heights of creativity and expression. Learn more about Ryan's experimentation with Respeecher here.
Another critical benefit of voice cloning for the music industry is streamlining music production for video games. These types of projects demand a high level of audio support, and producing soundtracks with recorded songs by real artists is extremely expensive for video game producers. Voice cloning allows sound designers to produce songs from musical scores and text using existing voices, thus reducing costs and expediting the production process. Additionally, the integration of deepfake audio technology further enhances the realism of generated vocals in video game soundtracks.
Artists who want to reach a global audience with their message by appealing to different groups of people worldwide can also benefit from cross-lingual singing voice synthesis. On the fourth anniversary of famous Swedish musician Tim Bergling, known professionally as Avicii, one of his best-known collaborators, Aloe Blacc, paid tribute to the artist. With the help of Respeecher's voice cloning technology, he performed and recorded Avicii's hit "Wake Me Up" in English, Mandarin, Spanish, Italian and French. In doing so, he aimed to allow more people around the world to appreciate Avicii's great talent gone too soon, showcasing the power of voice changer software to bridge language barriers and unite listeners across diverse cultures.
Another example of leveraging voice cloning for the music industry was when Elvis Presley's image and voice were recreated so he could take the stage for the first night of the America's Got Talent (AGT) season finale. Synthetic media developer Metaphysic showed off the digital King of Rock n' Roll performing songs and dancing. The audio performance was made possible by Respeecher, of course, showcased the remarkable capabilities of AI singers in resurrecting iconic voices and preserving musical legacies for new generations to enjoy, with the assistance of the best voice changer technology available.
Voting for experiments
Besides helping musicians and composers save time and resources, voice cloning delivers greater flexibility and offers new tools for self-expression and experimentation. With the integration of voice AI, Respeecher provides innovative solutions that enable artists to explore novel avenues of creativity and push the boundaries of musical expression.
At Respeecher, we are always eager to try something new. Even the craziest ideas should have a chance, and we are here to help you follow your dreams and unleash your talents.
