What you can do in Lyro
Lyro is an AI music studio that turns a description, a vocal or a beat into a finished, mixed and mastered song. These are the tools, each with a page that explains how it works and where its limits are.
AI song generator
Lyro’s AI song generator turns a text description, with or without lyrics, into a complete song: instruments, a sung vocal and a produced mix. You describe the genre, mood and voice. Lyro picks the model by the job: sung lyrics go to Google’s Lyria 3 Pro, which came first in the one small blind test we have run. You get a track you can download as MP3 or FLAC. A Lyria 3 Pro song costs 4 credits, whatever its length.
AI beat maker
Lyro’s AI beat maker generates an instrumental, with no vocals, from a description of the genre, tempo and instruments. When the beat has to hold an exact tempo and key, for example because you will record or add a vocal over it later, Lyro routes it to ACE-Step 1.5. That model locks to the BPM and key you set and is priced by length: one credit per 30 seconds with the detailed pass, or one credit per minute with the fast pass. Instrumentals that do not need the lock go to Google’s Lyria 3 Pro at 4 credits a track.
AI vocal generator
Lyro’s AI vocal generator sings the lyrics you give it, in 12 languages and in voice types such as soulful female, deep male, rap or duet. It can sing inside a full generated song, or over a beat you upload, in which case the vocal comes back as an isolated stem. Sung lyrics go to Google’s Lyria 3 Pro by default, which scored 4.67 out of 5 for Turkish pronunciation in our one small internal blind test.
Add vocals to a beat
Upload a beat and Lyro adds a vocal to it in one of two ways. With lyrics, it generates a sung performance at your beat’s tempo and key, separates the voice and returns it as an isolated vocal stem, so your beat is never altered. Without lyrics, ACE-Step 1.5 listens to the beat and improvises a topline over it. Either way, the beat and the new vocal open together in the mixer.
Add a beat to your vocals
Upload or record a vocal and Lyro writes a beat around it. It detects the tempo and key of your voice in the browser, then ACE-Step 1.5 composes drums, bass and other instruments that follow your phrasing. You get back the full mix, and your original vocal stays on its own track in the mixer, so you can rebalance it against the new music, add effects and master the result.
Stem splitter
Lyro’s stem splitter separates a finished track into four stems: vocals, drums, bass and other. It works on songs you generated and on audio you upload. Use it to make an instrumental or an a cappella, to rebalance a mix, or to pull a vocal out for chopping. It costs one credit plus two per started minute, so 7 credits for a three-minute track, and is part of the Creator plan.
Mixing and mastering
Lyro has a multitrack mixer and a mastering stage that run in your browser, so they cost no credits. Bring a vocal and a beat, or stems from anywhere, and balance them with gain, pan, EQ, compression, reverb, delay and a tempo-synced pump. Mastering then brings the mix to a loudness target measured in LUFS, with a limiter and an A/B switch, and exports WAV.
AI lyrics generator
Lyro’s lyric writer drafts song lyrics in 12 languages: hooks, verses and short vocal-chop phrases. It can also tighten or translate lyrics you already have. It is a writing assistant built on a large language model. It costs no credits: requests count against a monthly allowance that comes with your plan. The lyrics go straight into the song generator, laid out with section tags such as [Verse] and [Chorus] that the music model follows when it sings.