Turn a description into a finished song

How the model is chosen

Lyro offers two models under its own names. The default follows the one blind listening test we have run so far: one rater, seven Turkish-language briefs and three models, on 21 September 2026, with the model names hidden from the person scoring.

• Lyro High is the default for songs, vocal chops and instrumentals. Its model came first in that test: 4.67 out of 5 for Turkish pronunciation and 4.57 overall. Sung Turkish always goes to Lyro High.
• Lyro Extra was added on 24 September 2026, after that test. By its provider’s account it gives richer arrangements and more expressive vocals, and it is made for English, German, Spanish, French, Hindi, Japanese, Korean and Portuguese. It is not made for Turkish yet: in our own check, one Turkish song on each model, Lyro Extra lost a verse, so the app holds it back for Turkish lyrics unless you confirm.

We have not blind-tested the other languages, and we have not run a test for each genre. Outside sung Turkish the recommendation is a working rule, not a measurement.

The model is shown on each track, and you can change the recommendation before you generate. The method is in How we test AI music models.

What you control

You control the brief, the words and the voice. You can leave everything else to Lyro.

• Genre and mood, or a free-text style prompt. The prompt generator and the prompt library give you wording that models follow.
• Lyrics, with section tags such as [Verse] and [Chorus], in any of 12 languages.
• The kind of vocal: a voice type such as soulful female, deep male, rap or duet, or vocal chops, or none.
• Tempo in BPM and musical key, if you want to set them.

Where the limits are

AI song generation is good, and it is not reliable in the way an instrument is.

• AI vocals can mispronounce words, especially names, slang and rare words. Respelling a word the way it sounds usually fixes it.
• The same prompt gives a different song every time. Plan on a few generations to get one you keep, and budget credits for that.
• The result is one mixed stereo file, not separate tracks. To rebalance it you need the stem splitter, which leaves some artefacts.
• A BPM and key you set are followed as guidance, not locked exactly. Check a render with the free BPM and key finder if the tempo has to be exact.
• You cannot ask for a real artist’s voice or name. Describe the sound instead.

Formats, credits and rights

A song costs 4 credits on Lyro High and 5 credits on Lyro Extra, whatever its length; vocal chops and instrumentals cost the same. Cover art is made only when you ask for it: 11 credits buys a 4096 × 4096 cover made for that song, the size streaming distributors ask for (at least 3000 × 3000), ready to download. If a generation fails or times out, every credit for it comes back automatically, with a notice in the app and a refund line in your credit history. MP3 and FLAC downloads are included on every plan, and so is WAV export from the studio; downloads are never counted or capped.

Every paid plan includes a commercial licence. As between you and us, you own whatever rights exist in your tracks. We do not promise that copyright protects them: in the United States, works generated entirely by AI are not copyrightable. Every download carries an ID3 tag declaring it AI-generated, and the audio also carries an inaudible watermark added by the model provider. See music rights.

Tips for a better first result

• Give the tempo as a number, such as “122 BPM”, not a word such as “mid-tempo”.
• Name instruments and their role: “rolling log drum bassline”, “warm electric piano chords”.
• Keep chorus lines short and identical on every repeat.
• Write numbers and abbreviations out as words, the way they should be sung.
• Change one thing at a time between generations, so you can hear what it did.