ACE Step

Generate music with lyrics from text using ACE-Step

Inference$ Commercial useFrom 1 credit per run

About ACE Step

Generate music with lyrics from text using ACE-Step

text-to-audiotext-to-music

Pricing

A run with the default settings costs 1 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

tagstextrequired

Comma-separated list of genre tags to control the style of the generated audio. Can also be supplied as `prompt`.

lyricstextareadefault: ""

Lyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song.

durationnumberdefault: 60

The duration of the generated audio in seconds.

enable_safety_checkerbooleandefault: true

Check input content for safety. Disabling requires account authorization.

number_of_stepsintegerdefault: 27

Number of steps to generate the audio.

seedinteger

Random seed for reproducibility. If not provided, a random seed will be used.

schedulerselectdefault: "euler"

Scheduler to use for the generation process.

Options: euler, heun

guidance_typeselectdefault: "apg"

Type of CFG to use for the generation process.

Options: cfg, apg, cfg_star

granularity_scaleintegerdefault: 10

Granularity scale for the generation process. Higher values can reduce artifacts.

guidance_intervalnumberdefault: 0.5

Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps)

guidance_interval_decaynumberdefault: 0

Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.

guidance_scalenumberdefault: 15

Guidance scale for the generation.

minimum_guidance_scalenumberdefault: 3

Minimum guidance scale for the generation after the decay.

tag_guidance_scalenumberdefault: 5

Tag guidance scale for the generation.

lyric_guidance_scalenumberdefault: 1.5

Lyric guidance scale for the generation.

More from ACE Step

ACE Step Prompt To Audio

Generate music from a simple prompt using ACE-Step

text-to-music

text-to-audio

ACE Step Audio To Audio

Generate music from a lyrics and example audio using ACE-Step

audio-edit

audio-to-audio

ACE Step Audio Inpaint

Modify a portion of provided audio with lyrics and/or style using ACE-Step

audio-inpaintaudio-repaint

audio-to-audio

ACE Step Audio Outpaint

Extend the beginning or end of provided audio with lyrics and/or style using ACE-Step

audio-outpaintaudio-extend

audio-to-audio

Related text to audio models

Elevenlabs Tts Eleven V3

Generate text-to-speech audio using Eleven-v3 from ElevenLabs.

audio

text-to-audio

Elevenlabs Music

Generate high quality, realistic music with fine controls using Elevenlabs Music!

musictext-to-music

text-to-audio

ElevenLabs TTS Multilingual v2

Generate multilingual text-to-speech audio using ElevenLabs TTS Multilingual v2.

audio

text-to-audio

Elevenlabs Music v2.5

Generate high quality, realistic music with fine controls using Elevenlabs Music v2.5!

musictext-to-music

text-to-audio

✦ new

ElevenLabs Sound Effects V3

Generate sound effects up to 30 seconds from a text prompt with ElevenLabs SFX v3, with optional seamless looping.

soundsfx

text-to-audio

Stable Audio 2.5

Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI

audio

text-to-audio

Lyria 3.5

Lyria 3.5 is Google DeepMind's latest music generation model, and you can generate almost any type of music with it

musictext-to-music

text-to-audio

Minimax Music 2.6

MiniMax Music 2.6 creates complete tracks with singing, backing music, and detailed arrangements from lyrics and a style description.

stylizedtransform

text-to-audio

music generator

CassetteAI’s model generates a 30-second sample in under 2 seconds and a full 3-minute track in under 10 seconds. At 44.1 kHz stereo audio, expect a level of professional consistency with no breaks, no squeaks, and no random interruptions in your creations.

musiccassetteai

text-to-audio

Lyria2

Lyria 2 is Google's latest music generation model, you can generate any type of music with this model.

musicstylized

text-to-audio

Lyria 3 Pro

Lyria 3 Pro is the latest music model from Google

audiosfx

text-to-audio

Seed Audio 1.0

Seed Audio 1.0 is a new audio model from Bytedance that can generate high-quality, natural sounding audio using text, reference audios or an image.

text-to-audio