Famous voices in cooperation with AI technology!
THE BEST VO + LEGAL AI
100% safe solutions for professionals.
VO+AI AGENCY
VO+AI is a joint project by professional voice-over artists and Mikrofonika , Poland’s first online voice bank. It’s the first solution that combines the talent and experience of popular, well-loved voices with the advantages of artificial intelligence. Built on legal foundations and fully secure for all parties, this unique system enables the use of voices familiar to audiences from radio, television, and the internet.
We are developing our own fully autonomous models, created from scratch while preserving the distinctive traits of each speaker. The tone, intonation, interpretation, and even breathing patterns – all carefully replicated to faithfully reflect our top voice-over artists.
We support, evaluate, and authorize external technological solutions to achieve a satisfying balance between innovation, client expectations, and the safety of our voices.
We protect our voice artists from the illegal use of their unique talents by providing continuous monitoring of social and traditional media. We also offer legal support beyond the borders of Poland.
Need true professionals for your AI? Offer your clients AI-generated texts brought to life by voices they’ve trusted for decades.
Listen how VO+AI sounds
BLOG - Step by step
The 9th National Meeting of Voice-Over Artists, organized by the Mikrofonika voice bank, was the perfect venue to showcase our achievements and …
A few days ago, we received an interesting inquiry from the US. ➡️ Request: 288 native Polish voices➡️ Project: 40–60 minutes of …
Yes, it’s true. We’ve been keeping it under wraps – but Maciej joined our project almost a year ago. Why the secrecy? …
One of the key aspects of our agreements with voice talents is protection against the illegal use of their voices. Our response …
Ethics and Legality
The development of AI technology carries a particular responsibility and presents us with new challenges. The world is changing, but some fundamental principles remain the same. Each person’s voice is their exclusive property, just like other unique characteristics of every voice-over artist: interpretation, emphasis, phrasing, and the vocal patterns developed over years of work.
It’s no secret that tech companies often disregard the basic rights of individuals whose voices are used publicly. They exploit digital resources without the consent of the publishers, broadcasters, and voice-over artists – the owners of these recordings. This must have legal consequences. And we ensure that these consequences are meaningful.
The VO+AI project demonstrates that it’s possible to reconcile the interests of all parties and present a product that is 100% legal and in line with fundamental principles. Every voice-over artist whose voice we’ve used in this project is confident that they will have full control over the project, and any potential profits from the use of the resulting voice model will be shared fairly. This is guaranteed by a clear and transparent agreement. Our partners can be sure that we will protect their rights, advocate on their behalf, and safeguard their voices from illegal use.
We consult our development philosophy with the voiceovers themselves, presenting it at the National Meeting of Voiceover Artists. Our agreements have been presented to the Voiceover Association of the Republic of Poland, ZASP and the Professional Union of Dubbing Artists.
VO+AI is not intended to replace voice-over artists with technology. However, it understands the benefits of collaboration between voice-over artists and technology. It aims to open up new possibilities for clients to use the human voice in their AI projects. It is designed to make it easier to select the right performer. It helps editors fix troublesome mistakes and helps producers realize the variety of options available. It also saves voice-over artists time and enables them to accomplish tasks that are physically impossible to perform.
Co-create better productions.
Technology
In simple terms, our goal is to enable the creation of an accurate digital copy of every voice. Based on completed recordings, we analyze, using AI, the sound, articulation, interpretation, phrasing, and breathing of individual voice-over artists. We aim to faithfully replicate these variables when generating speech sounds from a provided text file. This is known as TTS (text-to-speech).
Our work is based on publicly available technologies. We use MIT-licensed solutions, such as GradTTS and HiFi-GAN. We modify and improve the proprietary engine created by Marcin Hajdukiewicz, one of the pioneers of TTS technology in Poland, who has been developing AI-based solutions since 2021.
We are constantly seeking new, inspiring technical solutions that would enable even better results. We are ready for new challenges and eager to contribute to the development of artificial intelligence.
The project is supported by
