AI Song Generator — Songs from Your Lyrics

With Suno v5.5 — the newest available version. We move to a newer model as soon as the provider ships one and it proves stable; the line under the generate button and the caption under a finished track always show the version the track was actually made with.

Yes — for your own timbre there is a separate tool, «Cover in your own voice» (voice-cover): record yourself singing and AI turns it into a clean studio vocal in your voice. The «Re-sing with AI voice» button here recreates your recording but sings it in an AI voice, not yours. And if you need literally your live voice over a backing track, mix your recording with the instrumental in the Audio Mixer.

We pass on to you all the rights we receive from the generation provider — to the extent the provider grants them; that covers commercial use and YouTube monetization. The terms of the provider can change, and we cannot guarantee them for the future. Uniqueness and copyright protectability under applicable law are not guaranteed either — similar melodies may be generated by other users.

If the generation is interrupted by a technical error, the tokens return to your balance automatically — you will see the "Tokens refunded automatically" badge next to the error message. A result that finished but simply is not to your taste is not refunded — that is the nature of generative models; make a targeted edit to the lyrics or style and run it again.

Every generation runs on the provider's GPU servers and has a real compute cost. Tokens cover that cost: you only pay for the runs you start, with no subscription.

Mark the structure with [Verse], [Chorus], [Bridge] so the AI knows where the verse and the chorus are. Keep lines under ~13 syllables so they fit the beat, and add stress marks to rare words and names with the "Add stress marks" button.

Usually 1–2 minutes, longer at peak hours. The result is two song variants in MP3: compare them, download either one or send it to the neighboring joining and video tools.

Every song you make sits in the «My songs» block right under the create button, and on the «My generations» page — with its cover art, its lyrics and a link back into the tool to keep working on the track. Ones you no longer need can go to the bin: they leave the list but stay recoverable. The storage deadline is printed under each song — download the ones that matter as soon as they are ready.

Yes. Every song in the «My songs» list has a «Repeat» button that puts that song's exact settings back into the form — style, lyrics, voice, length. Change what you need and run it again; the earlier song stays where it is, so you can compare the versions.

Not yet, and this one is easy to misread. The «Re-sing with an AI voice» button does take your file, but it re-creates the track: the AI listens to your music and makes its own version — your recording does not survive into the result. Laying a vocal over your own backing track is a separate capability we have not connected yet. If you want your own live singing over an instrumental, mix your recording with the backing track in the Audio mixer.

No. We measured this across 418 finished songs: at the same chosen length the track comes out the same, with breaks and without. The length is set by the «Desired length» field; breaks simply hand part of that time to the music instead of the singing. They help when there are few lyrics: a short text still has to fill the chosen length, and breaks keep the singing from being stretched. The estimate under the lyrics field counts only sung lines — use it to judge the amount of singing, and read the final length off the chosen step.

Put them in the «Exclude» field under the style: it travels to the model as a separate prohibition and works more reliably than the same words inside the description. Then re-read the style text itself — phrases like «vocal harmonies», «backing vocals», «choir» or «anthemic chorus» order backing singers even when a later line says you do not want them. Name the voice outright: «male voice, baritone». If you use the «Improve style» button, read what it produced: both the voice and your prohibitions must still be there.