Music to your ears, literally: Gemini now writes and produces songs

Source: Android Authority

Gemini imagined as a music composer and songwriter. Image created with Gemini.

TL;DR

• Gemini can now create entire songs, including lyrics, with just text or image prompts.
• It also generates accompanying album art for the track using Nano Banana.
• The feature is available widely for both free and paid users.

Gemini’s Evolution Toward Audio

Over the recent years, Gemini has really stepped up its game. The recent Gemini 3 update improved its photo and video quality to an unrealistically high standard, while the more recent deep thinking upgrade further enhanced its coding and research capabilities. After excelling at text, image, video, and code generation, Gemini is now turning its attention to audio—specifically, music.

With today’s update, Gemini takes a big leap in AI‑powered music generation, allowing users to create music with a simple text or image prompt. This functionality is powered by Google DeepMind’s new and updated Lyria 3 text‑to‑audio model. While earlier versions of Lyria were limited to experimental tools such as MusicFX or PromptDJ, Google is now making it accessible to a much broader audience through the Gemini mobile apps and web interface, as we noted last month (Android Authority article).

Google says users can describe a concept or upload an image, and Gemini will convert it into a “high‑quality, catchy track.” The new feature also generates lyrics and produces music that includes a complex, melodious mix of tastefully layered instruments. So far, apps such as Suno have dominated AI‑generated music, but Gemini now offers a comparable, fully integrated solution.

Previous Lyria models produced limited samples that required human expertise for layering and arranging into a full piece. They could also generate short instrumental clips for YouTube Shorts or the Recorder app on Pixel 9 and 10 series phones, but those were mainly filler or background music.

With this update, Gemini can create 30‑second tracks accompanied by album art generated with Gemini Nano. Users can tweak various aspects of the track—tempo, music style, singing style—through additional instructions, and they can even provide existing music for Gemini to use as inspiration.

Preventing Unauthorized Use of Copyrighted Tracks

Google maintains a firm stance against copying original music. Each generated track includes a hidden SynthID to help platforms differentiate AI‑generated music from human‑created works. Google notes that it has been “mindful of copyright and partner agreements” while training the new model and claims it will not mimic existing artists. Output tracks are tested against existing musical content to avoid infringement, and users can report any seemingly copied music that slips through.

Unlike other Gemini experiments, Google is going all‑in with music creation. The feature is launching in beta across several languages, including English, French, Hindi, German, Japanese, Korean, Portuguese, and Spanish. In addition to Gemini, the capability will also be available through the Dream Track audio generator for YouTube Shorts.

The feature is available to both free and paying Gemini users, though the amount of available credits depends on subscription status.