Music models
45 models. Compare AI music generation models by input — a text prompt or lyrics — and by output length and pricing unit.
Music, on Infery.ai
Music is its own catalogue category, separate from text-to-speech and speech-to-text: most of it generates an instrumental or vocal track from a text prompt. A small number also require a reference audio clip — voice cloning is the clear case, where the model needs a sample of the voice it's meant to sing in, not just a description of one.
One prompt, 4 models. Credits are what each run actually cost.
It is a catalogue, not one model
Models differ in whether they accept lyrics as a direct input alongside a style description — ace-step, for one, takes both a lyrics field and a tags field, where most models take a single prompt — and in maximum track length. Pricing unit varies more here than in any other modality: per-second and per-image are tied as the two most common, but per-operation, per-character, per-request, per-minute, per-megapixel and per-token pricing all appear too — eight units in total, so no single price-per-track figure applies across the category.
All 45 music models
Filter by provider, price and capability. Open one for its rates, accepted inputs and schema.
45 of 45 models
Open the Studio with a music model already picked
Free trial credits, no card. Filter above, or start from a blank chat and pick as you go.