Suno, the AI music creation service, has launched Visuals, a new tool that turns songs into images and short videos. Users can drag a song from their library to make clips up to 15 seconds long, with lip sync and lyric videos. It is available on the web now, with iOS and Android versions due in the coming weeks.
Visuals lets users make lyric videos, album art, and video clips from photos, all built around their songs.
Clips can be up to 15 seconds long and can be extended, edited, and re-prompted with text.
Users can start with built-in original characters or upload their own image.
Visuals is on the web now, with iOS and Android apps coming in the next few weeks.
Suno has released Suno Bridge, which lets musicians create instrument and vocal parts directly inside their music production software. It is currently a beta for Ableton Live 12 on Mac only. Premier subscribers get it at no extra cost.
Bridge is a separate app that must run alongside Ableton Live.
It creates new instruments and vocals that match a track's tempo, key, and groove, and places them on the timeline.
Session files are uploaded to Suno so it can understand the song, and the loop markers set the section to generate.
Support for other operating systems and music software is planned for later.
Suno users can now begin a song from a MIDI file, a format that stores notes and timing but no sound. You drag the file onto the Create page or choose MIDI from the plus menu. You can also decide whether Suno plays your notes exactly or grows a new idea from part of the melody.
Because a MIDI file holds only notes and timing, it offers a far more precise starting point than other inputs.
You choose how closely Suno follows the file, from exact playback to developing a short motif into a new song.
MIDI was created in the mid-1980s so devices such as synthesizers could exchange performance data.
Turning MIDI into a rich sound used to take costly instrument plugins, a lot of time and specialist skills.
Suno released Speech in beta, an audio model that creates spoken voice and background music together as one track. You enter an idea, a poem or your own writing, then describe the voice and musical style you want. After a month of testing with a small group, the beta is now open to everyone.
Suno describes Speech as the first audio model to produce speech and music in one combined track.
It is built right into Suno, so you only need to add your text and describe the voice and musical mood.
Suggested uses include meditations, poetry readings, pep talks and bedtime stories for kids.
As a beta it still has rough spots such as wandering accents, and Suno says it will keep improving it.
Suno released v6, a new generation of music models built with industry partners including Warner Music Group, BMG and Believe. Suno says the models are quicker, more expressive and of higher quality, with new features for finer control over songs. v6 comes as three models for different needs.
The flagship v6 is for Pro and Premier subscribers and turns out polished songs reliably in any genre.
v6-wild, also for Pro and Premier, is less predictable and gives varied results that spark new ideas.
v6-mini, a quicker and lighter model, is open to all users.
New tools let you edit part of a song in plain language, mash up several songs and build beats from samples.