What you can make
Music and sound
The tools that make music, sound effects and speech, and the two that get audio onto a clip.
If a board review needs something under it, **music-gen** writes a track from a description. It opens on **Lyria 3.5**, which writes a whole song with a real arrangement and can sing. Lyria has no length slider and no Instrumental switch, so say in the prompt how long the track should run and whether it has a voice. The model pill on the same card holds three more. **ElevenLabs Music v2.5** and **ElevenLabs Music v2** also write full arrangements, with singing when the prompt asks for it, and they add a **Duration** slider and an **Instrumental** switch. **Sonilo v1.1** is the cheap bed: give it a line like "warm lo-fi piano, slow tempo, vinyl dust" and it returns 10 seconds to 3 minutes of it, instrumental, priced by the second. The two ElevenLabs models are priced differently, and it is worth knowing before you run one. They are billed **per whole minute, rounded up**, and the model returns a little more audio than you ask for. A 60 second track is therefore billed as two minutes and costs 180 credits, where Sonilo stays at 12 for 30 seconds. Each step of the length slider adds a minute. v2.5 is the newer of the two and they cost the same, so reach for v2 only if you prefer what it does. **elevenlabs-sfx** makes single sounds. Describe one, get a clean mp3 between 1 and 22 seconds, and switch on Loop for a version that repeats without an audible join, made for ambience beds. Fire it and walk away: generation survives a refresh and the audio card appears on the canvas when it is ready. **ace-instrument** is the experimental one. It drives ACE-Step through a set of semantic pills, and its gear panel exposes the model's real synthesis knobs, guidance and granularity and scheduler among them. Instrumental only, 8 seconds to 3 minutes. ## Getting it onto a clip **mmaudio-v2** watches a silent video and generates audio synced to what happens on screen. What comes back is your same clip with the track baked in, as one playable mp4, anywhere from 1 to 30 seconds. Leave the prompt blank and it scores the clip on its own; write a direction and it follows. ## What is still rough The generated audio is the least developed part of Plnty. **ace-instrument** is openly experimental, and **mmaudio-v2** frequently returns something that is synchronised without being good. Both are being worked on. Use them for a scratch track and reach for a real composer when the piece matters.If a board review needs something under it, music-gen writes a track from a description. It opens on Lyria 3.5, which writes a whole song with a real arrangement and can sing. Lyria has no length slider and no Instrumental switch, so say in the prompt how long the track should run and whether it has a voice.
The model pill on the same card holds three more. ElevenLabs Music v2.5 and ElevenLabs Music v2 also write full arrangements, with singing when the prompt asks for it, and they add a Duration slider and an Instrumental switch. Sonilo v1.1 is the cheap bed: give it a line like “warm lo-fi piano, slow tempo, vinyl dust” and it returns 10 seconds to 3 minutes of it, instrumental, priced by the second.
The two ElevenLabs models are priced differently, and it is worth knowing before you run one. They are billed per whole minute, rounded up, and the model returns a little more audio than you ask for. A 60 second track is therefore billed as two minutes and costs 180 credits, where Sonilo stays at 12 for 30 seconds. Each step of the length slider adds a minute. v2.5 is the newer of the two and they cost the same, so reach for v2 only if you prefer what it does.
elevenlabs-sfx makes single sounds. Describe one, get a clean mp3 between 1 and 22 seconds, and switch on Loop for a version that repeats without an audible join, made for ambience beds. Fire it and walk away: generation survives a refresh and the audio card appears on the canvas when it is ready.
ace-instrument is the experimental one. It drives ACE-Step through a set of semantic pills, and its gear panel exposes the model’s real synthesis knobs, guidance and granularity and scheduler among them. Instrumental only, 8 seconds to 3 minutes.
Getting it onto a clip
Section titled “Getting it onto a clip”mmaudio-v2 watches a silent video and generates audio synced to what happens on screen. What comes back is your same clip with the track baked in, as one playable mp4, anywhere from 1 to 30 seconds. Leave the prompt blank and it scores the clip on its own; write a direction and it follows.
What is still rough
Section titled “What is still rough”The generated audio is the least developed part of Plnty. ace-instrument is openly experimental, and mmaudio-v2 frequently returns something that is synchronised without being good. Both are being worked on. Use them for a scratch track and reach for a real composer when the piece matters.