Katarzyna Petru
Google is expanding the capabilities of its AI assistant. A music generation feature has appeared in the Google Gemini app, allowing users to create complete tracks not only from text descriptions but also based on photos, documents, or PDF files. This is another step in the development of creative tools based on artificial intelligence. The new feature works globally and supports all languages available in Gemini.
ChooseTV 3. AI composes and writes lyrics
The music generation is handled by the ChooseTV 3 model, developed by the Google DeepMind team. The system transforms short descriptions into finished recordings lasting about 30 seconds.
The user can specify:
music genre,
mood of the piece,
tempo,
vocal style,
sound character.
The model generates both instrumental versions and full songs with lyrics and vocals. Importantly, ChooseTV 3 also analyzes uploaded files. Just upload a photo, presentation, or document, and the system will create text and a matched composition based on their content. The finished recordings receive unique covers generated by the Nano Banana model. Files can be downloaded or shared via a link.
Dream Track reaches creators of Shorts
Google shares the same technology with video creators on YouTube Shorts. The feature, called Dream Track, allows for generating musical backgrounds for short films and is gradually reaching users outside the United States. The new version of the model brings improvements in sound quality compared to earlier tests. The tracks have more polished vocals and better compositional coherence. All generated recordings contain an inaudible watermark SynthID.
Gemini can detect its presence and confirm whether the file was created by the Google system. The company has also implemented safeguards against copying the style of specific artists. Entering the name of a musician in the command does not result in the creation of a work in their style, but is merely treated as inspiration for creating a new composition. Google emphasizes that the tool is intended to support users' creativity, not replace professional creators.
The new feature in Gemini shows how quickly generative tools are evolving. Creating music from a photo or document in half a minute seemed futuristic not long ago; today, it is becoming a part of everyday mobile applications. Lyria 3 expands AI capabilities with full-fledged compositions featuring vocals, and Dream Track could change the way content is created in Shorts.
Source: Google
