In addition, Google has developed a second tool called Music AI, which allows artists in YouTube’s incubator program to create, remix, and modify tracks in new ways. The company is using a technology called Synth-ID to add inaudible watermarks to music generated using the AI, to ensure it can be identified. Despite concerns from some artists about the use of their work in AI systems’ training data without permission or payment, several musicians have embraced the AI revolution and are hopeful about the potential of these tools.
Key takeaways:
- Google has introduced an AI feature called Dream Track for YouTube Shorts creators, which can generate songs in the styles of seven different artists including Charlie Puth, Demi Lovato, Sia, and T-Pain.
- Dream Track uses an AI algorithm called Lyria developed by Google Deepmind. The tool can generate a full instrumental melody and backing track from a whistled tune, and convert abstract text input into a musical interpretation.
- Google is exploring how artists whose work helped train its music-generating algorithms will receive a cut of future ad revenue generated by videos featuring AI-generated audio. This represents a new way for artists to profit from AI built in part on their work.
- Google is also using a technology called Synth-ID to add inaudible watermarks to music generated using Lyria, allowing it to be identified as AI-generated. The company says Lyria was trained on a broad set of music content.