ACE-Step v1.5 XL SFT
ACE-Step v1.5 XL SFT is the supervised fine-tuned 4B DiT variant in the ACE-Step 1.5 XL line. It is positioned as the highest-quality XL option, combining 50-step CFG inference with stronger prompt adherence and refined audio quality for text-to-music, cover, and repaint workflows when final output quality matters more than speed or broader editing task coverage.

API Reference
INTEGRATE
Complete technical specification for integration
RequestResponse
Examples4
CODE
Ready-to-use code snippets for common workflows
text-to-audio
Retro Tech Podcast Theme Song$0.0039~13s0:00
import { createClient } from '@runware/sdk'
const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()
const [result] = await client.run({
model: 'runware:ace-step@v1.5-xl-sft',
positivePrompt: 'Original retro-futurist electro-soul podcast intro with crisp broken-beat production and the intrigue of a technology documentary. Feature punchy Linn-style drums, warm analog synth bass, glassy electric piano, muted funk guitar, arpeggiated monosynth, and brief vocoder responses. A close-miked female contralto sings with calm authority, precise diction, and understated curiosity; melodic throughout rather than spoken. Polished, intelligent, kinetic, and slightly mysterious without becoming ominous. Build a complete 60-second arrangement: four-bar instrumental hook, restrained verse, rising pre-chorus, memorable full chorus with layered harmonies, then a clean branded outro sting. Keep the lead vocal prominent and every lyric intelligible. Broadcast-ready mix with tight low end, dry drums, subtle stereo synth motion, and a decisive ending rather than a fade.',
duration: 60,
settings: {
lyrics: '[Intro]\nUnder the floor, behind the light,\nYesterday is working through the night.\n\n[Verse]\nEvery little circuit has a maker and a date,\nA factory, a promise, and a twist of hidden fate.\nFrom traffic lights to satellites, the old machines persist;\nWe follow every signal that the future somehow missed.\n\n[Pre-Chorus]\nTrace the hands, decode the signs,\nHistory hums between the lines.\n\n[Chorus]\nSilicon Afterlife,\nWhere the buried systems come alive.\nChip by chip and wire by wire,\nWe find the ghosts inside the fire.\nSilicon Afterlife,\nOld ideas that still survive.\nPower down, but stories stay alive.\n\n[Outro]\nSilicon Afterlife.',
bpm: 118,
keyScale: 'D minor',
timeSignature: 4,
vocalLanguage: 'en'
}
})import asyncio
import os
from runware import Runware
async def main():
async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
results = await client.run({
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Original retro-futurist electro-soul podcast intro with crisp broken-beat production and the intrigue of a technology documentary. Feature punchy Linn-style drums, warm analog synth bass, glassy electric piano, muted funk guitar, arpeggiated monosynth, and brief vocoder responses. A close-miked female contralto sings with calm authority, precise diction, and understated curiosity; melodic throughout rather than spoken. Polished, intelligent, kinetic, and slightly mysterious without becoming ominous. Build a complete 60-second arrangement: four-bar instrumental hook, restrained verse, rising pre-chorus, memorable full chorus with layered harmonies, then a clean branded outro sting. Keep the lead vocal prominent and every lyric intelligible. Broadcast-ready mix with tight low end, dry drums, subtle stereo synth motion, and a decisive ending rather than a fade.",
"duration": 60,
"settings": {
"lyrics": "[Intro]\nUnder the floor, behind the light,\nYesterday is working through the night.\n\n[Verse]\nEvery little circuit has a maker and a date,\nA factory, a promise, and a twist of hidden fate.\nFrom traffic lights to satellites, the old machines persist;\nWe follow every signal that the future somehow missed.\n\n[Pre-Chorus]\nTrace the hands, decode the signs,\nHistory hums between the lines.\n\n[Chorus]\nSilicon Afterlife,\nWhere the buried systems come alive.\nChip by chip and wire by wire,\nWe find the ghosts inside the fire.\nSilicon Afterlife,\nOld ideas that still survive.\nPower down, but stories stay alive.\n\n[Outro]\nSilicon Afterlife.",
"bpm": 118,
"keyScale": "D minor",
"timeSignature": 4,
"vocalLanguage": "en"
}
})
asyncio.run(main())curl https://api.runware.ai/v1 \
-H "Authorization: Bearer $RUNWARE_API_KEY" \
-H "Content-Type: application/json" \
-d '[
{
"taskType": "audioInference",
"taskUUID": "115e410c-4433-4ac9-b165-01d5a6250693",
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Original retro-futurist electro-soul podcast intro with crisp broken-beat production and the intrigue of a technology documentary. Feature punchy Linn-style drums, warm analog synth bass, glassy electric piano, muted funk guitar, arpeggiated monosynth, and brief vocoder responses. A close-miked female contralto sings with calm authority, precise diction, and understated curiosity; melodic throughout rather than spoken. Polished, intelligent, kinetic, and slightly mysterious without becoming ominous. Build a complete 60-second arrangement: four-bar instrumental hook, restrained verse, rising pre-chorus, memorable full chorus with layered harmonies, then a clean branded outro sting. Keep the lead vocal prominent and every lyric intelligible. Broadcast-ready mix with tight low end, dry drums, subtle stereo synth motion, and a decisive ending rather than a fade.",
"duration": 60,
"settings": {
"lyrics": "[Intro]\nUnder the floor, behind the light,\nYesterday is working through the night.\n\n[Verse]\nEvery little circuit has a maker and a date,\nA factory, a promise, and a twist of hidden fate.\nFrom traffic lights to satellites, the old machines persist;\nWe follow every signal that the future somehow missed.\n\n[Pre-Chorus]\nTrace the hands, decode the signs,\nHistory hums between the lines.\n\n[Chorus]\nSilicon Afterlife,\nWhere the buried systems come alive.\nChip by chip and wire by wire,\nWe find the ghosts inside the fire.\nSilicon Afterlife,\nOld ideas that still survive.\nPower down, but stories stay alive.\n\n[Outro]\nSilicon Afterlife.",
"bpm": 118,
"keyScale": "D minor",
"timeSignature": 4,
"vocalLanguage": "en"
}
}
]'runware run runware:ace-step@v1.5-xl-sft \
positivePrompt="Original retro-futurist electro-soul podcast intro with crisp broken-beat production and the intrigue of a technology documentary. Feature punchy Linn-style drums, warm analog synth bass, glassy electric piano, muted funk guitar, arpeggiated monosynth, and brief vocoder responses. A close-miked female contralto sings with calm authority, precise diction, and understated curiosity; melodic throughout rather than spoken. Polished, intelligent, kinetic, and slightly mysterious without becoming ominous. Build a complete 60-second arrangement: four-bar instrumental hook, restrained verse, rising pre-chorus, memorable full chorus with layered harmonies, then a clean branded outro sting. Keep the lead vocal prominent and every lyric intelligible. Broadcast-ready mix with tight low end, dry drums, subtle stereo synth motion, and a decisive ending rather than a fade." \
duration=60 \
settings.lyrics="[Intro]
Under the floor, behind the light,
Yesterday is working through the night.
[Verse]
Every little circuit has a maker and a date,
A factory, a promise, and a twist of hidden fate.
From traffic lights to satellites, the old machines persist;
We follow every signal that the future somehow missed.
[Pre-Chorus]
Trace the hands, decode the signs,
History hums between the lines.
[Chorus]
Silicon Afterlife,
Where the buried systems come alive.
Chip by chip and wire by wire,
We find the ghosts inside the fire.
Silicon Afterlife,
Old ideas that still survive.
Power down, but stories stay alive.
[Outro]
Silicon Afterlife." \
settings.bpm=118 \
settings.keyScale="D minor" \
settings.timeSignature=4 \
settings.vocalLanguage=en{
"taskType": "audioInference",
"taskUUID": "115e410c-4433-4ac9-b165-01d5a6250693",
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Original retro-futurist electro-soul podcast intro with crisp broken-beat production and the intrigue of a technology documentary. Feature punchy Linn-style drums, warm analog synth bass, glassy electric piano, muted funk guitar, arpeggiated monosynth, and brief vocoder responses. A close-miked female contralto sings with calm authority, precise diction, and understated curiosity; melodic throughout rather than spoken. Polished, intelligent, kinetic, and slightly mysterious without becoming ominous. Build a complete 60-second arrangement: four-bar instrumental hook, restrained verse, rising pre-chorus, memorable full chorus with layered harmonies, then a clean branded outro sting. Keep the lead vocal prominent and every lyric intelligible. Broadcast-ready mix with tight low end, dry drums, subtle stereo synth motion, and a decisive ending rather than a fade.",
"duration": 60,
"settings": {
"lyrics": "[Intro]\nUnder the floor, behind the light,\nYesterday is working through the night.\n\n[Verse]\nEvery little circuit has a maker and a date,\nA factory, a promise, and a twist of hidden fate.\nFrom traffic lights to satellites, the old machines persist;\nWe follow every signal that the future somehow missed.\n\n[Pre-Chorus]\nTrace the hands, decode the signs,\nHistory hums between the lines.\n\n[Chorus]\nSilicon Afterlife,\nWhere the buried systems come alive.\nChip by chip and wire by wire,\nWe find the ghosts inside the fire.\nSilicon Afterlife,\nOld ideas that still survive.\nPower down, but stories stay alive.\n\n[Outro]\nSilicon Afterlife.",
"bpm": 118,
"keyScale": "D minor",
"timeSignature": 4,
"vocalLanguage": "en"
}
}Response
{
"taskType": "audioInference",
"taskUUID": "115e410c-4433-4ac9-b165-01d5a6250693",
"audioUUID": "4881df69-1f80-46ad-b51e-625cafba4d7e",
"audioURL": "https://am.runware.ai/audio/os/a02d21/ws/5/ai/4881df69-1f80-46ad-b51e-625cafba4d7e.mp3",
"seed": 1947966619,
"cost": 0.0039
}audio-driven
Flooded Archive Salvage Audio Lesson$0.0144~32s0:00
import { createClient } from '@runware/sdk'
const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()
const [result] = await client.run({
model: 'runware:ace-step@v1.5-xl-sft',
positivePrompt: 'Reinterpret the entire supplied track as a polished e-learning narration clip for museum and library disaster-response training. Make the transformation immediately noticeable: replace the source\'s retro funk instrumentation with prepared piano, bass clarinet, restrained cello harmonics, brushed frame drum, soft analog pulse, and subtle room tone suggesting a quiet conservation laboratory after a flood. Retain the recognizable three-note lead motif, syncopated bass rhythm, steady pulse, four-part arrangement, major transition points, and final resolution from the source. The mood is calm urgency rather than drama. Use an articulate, reassuring adult female narrator with a natural instructional cadence, precise consonants, and brief pauses between actions. Speak, do not sing, the following text verbatim: “When water reaches a paper collection, begin with safety, not speed. Confirm the electricity is isolated, wear nitrile gloves, and photograph each shelf before moving anything. Separate wet volumes from damp ones. Support saturated books from beneath; never pull them by the spine. Interleave only when pages can open without resistance. Freeze material that cannot be air-dried within forty-eight hours. Label every crate with room, shelf, and sequence. The goal is not to make objects look dry. The goal is to preserve evidence, order, and options for the conservator.” Keep the narration centered, intimate, and consistently intelligible. Shape the arrangement around the speech with subtle musical ducking, using the instrumental opening and closing to present the retained motif clearly. Finished editorial audio with balanced dynamics and refined documentary sound.',
negativePrompt: 'Sung narration, chanting, rap delivery, theatrical acting, alarm sounds, cinematic impacts, horror atmosphere, excessive reverb, busy accompaniment beneath speech, distorted voice, doubled voice, background conversations, added words, omitted instructions, abrupt edit points, or an unresolved ending.',
strength: 0.55,
inputs: {
audio: 'https://assets.runware.ai/assets/inputs/8d839ab4-3add-4531-bd98-5149dd2e42f6.mp3'
}
})import asyncio
import os
from runware import Runware
async def main():
async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
results = await client.run({
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Reinterpret the entire supplied track as a polished e-learning narration clip for museum and library disaster-response training. Make the transformation immediately noticeable: replace the source's retro funk instrumentation with prepared piano, bass clarinet, restrained cello harmonics, brushed frame drum, soft analog pulse, and subtle room tone suggesting a quiet conservation laboratory after a flood. Retain the recognizable three-note lead motif, syncopated bass rhythm, steady pulse, four-part arrangement, major transition points, and final resolution from the source. The mood is calm urgency rather than drama. Use an articulate, reassuring adult female narrator with a natural instructional cadence, precise consonants, and brief pauses between actions. Speak, do not sing, the following text verbatim: “When water reaches a paper collection, begin with safety, not speed. Confirm the electricity is isolated, wear nitrile gloves, and photograph each shelf before moving anything. Separate wet volumes from damp ones. Support saturated books from beneath; never pull them by the spine. Interleave only when pages can open without resistance. Freeze material that cannot be air-dried within forty-eight hours. Label every crate with room, shelf, and sequence. The goal is not to make objects look dry. The goal is to preserve evidence, order, and options for the conservator.” Keep the narration centered, intimate, and consistently intelligible. Shape the arrangement around the speech with subtle musical ducking, using the instrumental opening and closing to present the retained motif clearly. Finished editorial audio with balanced dynamics and refined documentary sound.",
"negativePrompt": "Sung narration, chanting, rap delivery, theatrical acting, alarm sounds, cinematic impacts, horror atmosphere, excessive reverb, busy accompaniment beneath speech, distorted voice, doubled voice, background conversations, added words, omitted instructions, abrupt edit points, or an unresolved ending.",
"strength": 0.55,
"inputs": {
"audio": "https://assets.runware.ai/assets/inputs/8d839ab4-3add-4531-bd98-5149dd2e42f6.mp3"
}
})
asyncio.run(main())curl https://api.runware.ai/v1 \
-H "Authorization: Bearer $RUNWARE_API_KEY" \
-H "Content-Type: application/json" \
-d '[
{
"taskType": "audioInference",
"taskUUID": "a2da45c2-9af1-43cb-bf66-df5f2c3adda1",
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Reinterpret the entire supplied track as a polished e-learning narration clip for museum and library disaster-response training. Make the transformation immediately noticeable: replace the source's retro funk instrumentation with prepared piano, bass clarinet, restrained cello harmonics, brushed frame drum, soft analog pulse, and subtle room tone suggesting a quiet conservation laboratory after a flood. Retain the recognizable three-note lead motif, syncopated bass rhythm, steady pulse, four-part arrangement, major transition points, and final resolution from the source. The mood is calm urgency rather than drama. Use an articulate, reassuring adult female narrator with a natural instructional cadence, precise consonants, and brief pauses between actions. Speak, do not sing, the following text verbatim: “When water reaches a paper collection, begin with safety, not speed. Confirm the electricity is isolated, wear nitrile gloves, and photograph each shelf before moving anything. Separate wet volumes from damp ones. Support saturated books from beneath; never pull them by the spine. Interleave only when pages can open without resistance. Freeze material that cannot be air-dried within forty-eight hours. Label every crate with room, shelf, and sequence. The goal is not to make objects look dry. The goal is to preserve evidence, order, and options for the conservator.” Keep the narration centered, intimate, and consistently intelligible. Shape the arrangement around the speech with subtle musical ducking, using the instrumental opening and closing to present the retained motif clearly. Finished editorial audio with balanced dynamics and refined documentary sound.",
"negativePrompt": "Sung narration, chanting, rap delivery, theatrical acting, alarm sounds, cinematic impacts, horror atmosphere, excessive reverb, busy accompaniment beneath speech, distorted voice, doubled voice, background conversations, added words, omitted instructions, abrupt edit points, or an unresolved ending.",
"strength": 0.55,
"inputs": {
"audio": "https://assets.runware.ai/assets/inputs/8d839ab4-3add-4531-bd98-5149dd2e42f6.mp3"
}
}
]'runware run runware:ace-step@v1.5-xl-sft \
positivePrompt="Reinterpret the entire supplied track as a polished e-learning narration clip for museum and library disaster-response training. Make the transformation immediately noticeable: replace the source's retro funk instrumentation with prepared piano, bass clarinet, restrained cello harmonics, brushed frame drum, soft analog pulse, and subtle room tone suggesting a quiet conservation laboratory after a flood. Retain the recognizable three-note lead motif, syncopated bass rhythm, steady pulse, four-part arrangement, major transition points, and final resolution from the source. The mood is calm urgency rather than drama. Use an articulate, reassuring adult female narrator with a natural instructional cadence, precise consonants, and brief pauses between actions. Speak, do not sing, the following text verbatim: “When water reaches a paper collection, begin with safety, not speed. Confirm the electricity is isolated, wear nitrile gloves, and photograph each shelf before moving anything. Separate wet volumes from damp ones. Support saturated books from beneath; never pull them by the spine. Interleave only when pages can open without resistance. Freeze material that cannot be air-dried within forty-eight hours. Label every crate with room, shelf, and sequence. The goal is not to make objects look dry. The goal is to preserve evidence, order, and options for the conservator.” Keep the narration centered, intimate, and consistently intelligible. Shape the arrangement around the speech with subtle musical ducking, using the instrumental opening and closing to present the retained motif clearly. Finished editorial audio with balanced dynamics and refined documentary sound." \
negativePrompt="Sung narration, chanting, rap delivery, theatrical acting, alarm sounds, cinematic impacts, horror atmosphere, excessive reverb, busy accompaniment beneath speech, distorted voice, doubled voice, background conversations, added words, omitted instructions, abrupt edit points, or an unresolved ending." \
strength=0.55 \
inputs.audio=https://assets.runware.ai/assets/inputs/8d839ab4-3add-4531-bd98-5149dd2e42f6.mp3{
"taskType": "audioInference",
"taskUUID": "a2da45c2-9af1-43cb-bf66-df5f2c3adda1",
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Reinterpret the entire supplied track as a polished e-learning narration clip for museum and library disaster-response training. Make the transformation immediately noticeable: replace the source's retro funk instrumentation with prepared piano, bass clarinet, restrained cello harmonics, brushed frame drum, soft analog pulse, and subtle room tone suggesting a quiet conservation laboratory after a flood. Retain the recognizable three-note lead motif, syncopated bass rhythm, steady pulse, four-part arrangement, major transition points, and final resolution from the source. The mood is calm urgency rather than drama. Use an articulate, reassuring adult female narrator with a natural instructional cadence, precise consonants, and brief pauses between actions. Speak, do not sing, the following text verbatim: “When water reaches a paper collection, begin with safety, not speed. Confirm the electricity is isolated, wear nitrile gloves, and photograph each shelf before moving anything. Separate wet volumes from damp ones. Support saturated books from beneath; never pull them by the spine. Interleave only when pages can open without resistance. Freeze material that cannot be air-dried within forty-eight hours. Label every crate with room, shelf, and sequence. The goal is not to make objects look dry. The goal is to preserve evidence, order, and options for the conservator.” Keep the narration centered, intimate, and consistently intelligible. Shape the arrangement around the speech with subtle musical ducking, using the instrumental opening and closing to present the retained motif clearly. Finished editorial audio with balanced dynamics and refined documentary sound.",
"negativePrompt": "Sung narration, chanting, rap delivery, theatrical acting, alarm sounds, cinematic impacts, horror atmosphere, excessive reverb, busy accompaniment beneath speech, distorted voice, doubled voice, background conversations, added words, omitted instructions, abrupt edit points, or an unresolved ending.",
"strength": 0.55,
"inputs": {
"audio": "https://assets.runware.ai/assets/inputs/8d839ab4-3add-4531-bd98-5149dd2e42f6.mp3"
}
}Response
{
"taskType": "audioInference",
"taskUUID": "a2da45c2-9af1-43cb-bf66-df5f2c3adda1",
"audioUUID": "04b6c327-5a97-4b4c-adf3-6637d802e733",
"audioURL": "https://am.runware.ai/audio/os/a05d22/ws/5/ai/04b6c327-5a97-4b4c-adf3-6637d802e733.mp3",
"seed": 1546093490,
"cost": 0.0144
}audio-extend
Neutrino Observatory Ambient Extension$0.0115~31s0:00
import { createClient } from '@runware/sdk'
const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()
const [result] = await client.run({
model: 'runware:ace-step@v1.5-xl-sft',
positivePrompt: 'Continue the supplied underground neutrino observatory ambience seamlessly after its 30-second endpoint, appending audio through 45 seconds. Preserve the exact spatial character, noise floor, deep ventilation drone, cooling-water movement, restrained electrical hum, sparse relay ticks, photomultiplier-like clicks, and slow irregular machinery pulse already established. Develop the existing rhythm subtly: let the relay pattern become slightly more interconnected, introduce one distant low metal resonance, and allow a faint glassy electronic overtone to emerge from the hum. Keep the extension immersive, clinical, cavernous, and mysterious, suitable as a looping ambient bed for a science museum installation. Maintain realistic scale and smooth continuity at the join. No restart, transition cue, new genre, or obvious musical section. Finish still in motion with unresolved machinery and room tone.',
negativePrompt: 'Vocals, speech, choir, melody, drums, cinematic trailer hits, risers, alarms, sirens, explosions, jump scares, harsh distortion, abrupt edits, silence, fade-out, final chord, rhythmic reset, bright pop production',
strength: 0.65,
settings: {
repaintingStart: 24,
repaintingEnd: 45
},
inputs: {
audio: 'https://assets.runware.ai/assets/inputs/36f32b52-75dd-4fdd-b851-6492b1963bc6.mp3'
}
})import asyncio
import os
from runware import Runware
async def main():
async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
results = await client.run({
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Continue the supplied underground neutrino observatory ambience seamlessly after its 30-second endpoint, appending audio through 45 seconds. Preserve the exact spatial character, noise floor, deep ventilation drone, cooling-water movement, restrained electrical hum, sparse relay ticks, photomultiplier-like clicks, and slow irregular machinery pulse already established. Develop the existing rhythm subtly: let the relay pattern become slightly more interconnected, introduce one distant low metal resonance, and allow a faint glassy electronic overtone to emerge from the hum. Keep the extension immersive, clinical, cavernous, and mysterious, suitable as a looping ambient bed for a science museum installation. Maintain realistic scale and smooth continuity at the join. No restart, transition cue, new genre, or obvious musical section. Finish still in motion with unresolved machinery and room tone.",
"negativePrompt": "Vocals, speech, choir, melody, drums, cinematic trailer hits, risers, alarms, sirens, explosions, jump scares, harsh distortion, abrupt edits, silence, fade-out, final chord, rhythmic reset, bright pop production",
"strength": 0.65,
"settings": {
"repaintingStart": 24,
"repaintingEnd": 45
},
"inputs": {
"audio": "https://assets.runware.ai/assets/inputs/36f32b52-75dd-4fdd-b851-6492b1963bc6.mp3"
}
})
asyncio.run(main())curl https://api.runware.ai/v1 \
-H "Authorization: Bearer $RUNWARE_API_KEY" \
-H "Content-Type: application/json" \
-d '[
{
"taskType": "audioInference",
"taskUUID": "1a5d1cb8-c67d-4cc7-97ff-542df91fde86",
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Continue the supplied underground neutrino observatory ambience seamlessly after its 30-second endpoint, appending audio through 45 seconds. Preserve the exact spatial character, noise floor, deep ventilation drone, cooling-water movement, restrained electrical hum, sparse relay ticks, photomultiplier-like clicks, and slow irregular machinery pulse already established. Develop the existing rhythm subtly: let the relay pattern become slightly more interconnected, introduce one distant low metal resonance, and allow a faint glassy electronic overtone to emerge from the hum. Keep the extension immersive, clinical, cavernous, and mysterious, suitable as a looping ambient bed for a science museum installation. Maintain realistic scale and smooth continuity at the join. No restart, transition cue, new genre, or obvious musical section. Finish still in motion with unresolved machinery and room tone.",
"negativePrompt": "Vocals, speech, choir, melody, drums, cinematic trailer hits, risers, alarms, sirens, explosions, jump scares, harsh distortion, abrupt edits, silence, fade-out, final chord, rhythmic reset, bright pop production",
"strength": 0.65,
"settings": {
"repaintingStart": 24,
"repaintingEnd": 45
},
"inputs": {
"audio": "https://assets.runware.ai/assets/inputs/36f32b52-75dd-4fdd-b851-6492b1963bc6.mp3"
}
}
]'runware run runware:ace-step@v1.5-xl-sft \
positivePrompt="Continue the supplied underground neutrino observatory ambience seamlessly after its 30-second endpoint, appending audio through 45 seconds. Preserve the exact spatial character, noise floor, deep ventilation drone, cooling-water movement, restrained electrical hum, sparse relay ticks, photomultiplier-like clicks, and slow irregular machinery pulse already established. Develop the existing rhythm subtly: let the relay pattern become slightly more interconnected, introduce one distant low metal resonance, and allow a faint glassy electronic overtone to emerge from the hum. Keep the extension immersive, clinical, cavernous, and mysterious, suitable as a looping ambient bed for a science museum installation. Maintain realistic scale and smooth continuity at the join. No restart, transition cue, new genre, or obvious musical section. Finish still in motion with unresolved machinery and room tone." \
negativePrompt="Vocals, speech, choir, melody, drums, cinematic trailer hits, risers, alarms, sirens, explosions, jump scares, harsh distortion, abrupt edits, silence, fade-out, final chord, rhythmic reset, bright pop production" \
strength=0.65 \
settings.repaintingStart=24 \
settings.repaintingEnd=45 \
inputs.audio=https://assets.runware.ai/assets/inputs/36f32b52-75dd-4fdd-b851-6492b1963bc6.mp3{
"taskType": "audioInference",
"taskUUID": "1a5d1cb8-c67d-4cc7-97ff-542df91fde86",
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Continue the supplied underground neutrino observatory ambience seamlessly after its 30-second endpoint, appending audio through 45 seconds. Preserve the exact spatial character, noise floor, deep ventilation drone, cooling-water movement, restrained electrical hum, sparse relay ticks, photomultiplier-like clicks, and slow irregular machinery pulse already established. Develop the existing rhythm subtly: let the relay pattern become slightly more interconnected, introduce one distant low metal resonance, and allow a faint glassy electronic overtone to emerge from the hum. Keep the extension immersive, clinical, cavernous, and mysterious, suitable as a looping ambient bed for a science museum installation. Maintain realistic scale and smooth continuity at the join. No restart, transition cue, new genre, or obvious musical section. Finish still in motion with unresolved machinery and room tone.",
"negativePrompt": "Vocals, speech, choir, melody, drums, cinematic trailer hits, risers, alarms, sirens, explosions, jump scares, harsh distortion, abrupt edits, silence, fade-out, final chord, rhythmic reset, bright pop production",
"strength": 0.65,
"settings": {
"repaintingStart": 24,
"repaintingEnd": 45
},
"inputs": {
"audio": "https://assets.runware.ai/assets/inputs/36f32b52-75dd-4fdd-b851-6492b1963bc6.mp3"
}
}Response
{
"taskType": "audioInference",
"taskUUID": "1a5d1cb8-c67d-4cc7-97ff-542df91fde86",
"audioUUID": "49aba909-aed5-429a-9fab-3378bc652b72",
"audioURL": "https://am.runware.ai/audio/os/a05d22/ws/5/ai/49aba909-aed5-429a-9fab-3378bc652b72.mp3",
"seed": 1243800397,
"cost": 0.01155
}audio-repaint
Maritime Claims Podcast Segment Bumper$0.0096~24s0:00
import { createClient } from '@runware/sdk'
const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY })
await client.connect()
const [result] = await client.run({
model: 'runware:ace-step@v1.5-xl-sft',
positivePrompt: 'Replace only the musical passage from 8 to 18 seconds with new content for a premium investigative maritime-insurance podcast bumper. Preserve the untouched audio before and after the replacement. Instead of the source\'s bowed-vibraphone melody, create a tense but understated interlocking figure using dry marimba, muted prepared piano, and a low plucked cello ostinato. Add tiny metallic accents reminiscent of drafting tools and cargo seals, treated as refined percussion rather than literal sound effects. Keep the existing tempo, pulse, tonal center, intimate studio acoustics, and restrained analog warmth. Enter seamlessly from the prepared-piano rhythm at 8 seconds, develop a memorable four-note question-and-answer motif, then simplify during the final two seconds so the passage reconnects naturally and invisibly with the original material at 18 seconds. Editorial, intelligent, meticulous, and modern; no vocals, speech, sea shanty references, waves, foghorns, EDM drops, trailer booms, or abrupt splice.',
strength: 0.75,
settings: {
repaintingStart: 8,
repaintingEnd: 18
},
inputs: {
audio: 'https://assets.runware.ai/assets/inputs/a2be1c20-67e0-4321-8fc3-8a1fe2452b82.mp3'
}
})import asyncio
import os
from runware import Runware
async def main():
async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client:
results = await client.run({
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Replace only the musical passage from 8 to 18 seconds with new content for a premium investigative maritime-insurance podcast bumper. Preserve the untouched audio before and after the replacement. Instead of the source's bowed-vibraphone melody, create a tense but understated interlocking figure using dry marimba, muted prepared piano, and a low plucked cello ostinato. Add tiny metallic accents reminiscent of drafting tools and cargo seals, treated as refined percussion rather than literal sound effects. Keep the existing tempo, pulse, tonal center, intimate studio acoustics, and restrained analog warmth. Enter seamlessly from the prepared-piano rhythm at 8 seconds, develop a memorable four-note question-and-answer motif, then simplify during the final two seconds so the passage reconnects naturally and invisibly with the original material at 18 seconds. Editorial, intelligent, meticulous, and modern; no vocals, speech, sea shanty references, waves, foghorns, EDM drops, trailer booms, or abrupt splice.",
"strength": 0.75,
"settings": {
"repaintingStart": 8,
"repaintingEnd": 18
},
"inputs": {
"audio": "https://assets.runware.ai/assets/inputs/a2be1c20-67e0-4321-8fc3-8a1fe2452b82.mp3"
}
})
asyncio.run(main())curl https://api.runware.ai/v1 \
-H "Authorization: Bearer $RUNWARE_API_KEY" \
-H "Content-Type: application/json" \
-d '[
{
"taskType": "audioInference",
"taskUUID": "a11d34e4-b519-4f10-be3c-e724ce1a7b79",
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Replace only the musical passage from 8 to 18 seconds with new content for a premium investigative maritime-insurance podcast bumper. Preserve the untouched audio before and after the replacement. Instead of the source's bowed-vibraphone melody, create a tense but understated interlocking figure using dry marimba, muted prepared piano, and a low plucked cello ostinato. Add tiny metallic accents reminiscent of drafting tools and cargo seals, treated as refined percussion rather than literal sound effects. Keep the existing tempo, pulse, tonal center, intimate studio acoustics, and restrained analog warmth. Enter seamlessly from the prepared-piano rhythm at 8 seconds, develop a memorable four-note question-and-answer motif, then simplify during the final two seconds so the passage reconnects naturally and invisibly with the original material at 18 seconds. Editorial, intelligent, meticulous, and modern; no vocals, speech, sea shanty references, waves, foghorns, EDM drops, trailer booms, or abrupt splice.",
"strength": 0.75,
"settings": {
"repaintingStart": 8,
"repaintingEnd": 18
},
"inputs": {
"audio": "https://assets.runware.ai/assets/inputs/a2be1c20-67e0-4321-8fc3-8a1fe2452b82.mp3"
}
}
]'runware run runware:ace-step@v1.5-xl-sft \
positivePrompt="Replace only the musical passage from 8 to 18 seconds with new content for a premium investigative maritime-insurance podcast bumper. Preserve the untouched audio before and after the replacement. Instead of the source's bowed-vibraphone melody, create a tense but understated interlocking figure using dry marimba, muted prepared piano, and a low plucked cello ostinato. Add tiny metallic accents reminiscent of drafting tools and cargo seals, treated as refined percussion rather than literal sound effects. Keep the existing tempo, pulse, tonal center, intimate studio acoustics, and restrained analog warmth. Enter seamlessly from the prepared-piano rhythm at 8 seconds, develop a memorable four-note question-and-answer motif, then simplify during the final two seconds so the passage reconnects naturally and invisibly with the original material at 18 seconds. Editorial, intelligent, meticulous, and modern; no vocals, speech, sea shanty references, waves, foghorns, EDM drops, trailer booms, or abrupt splice." \
strength=0.75 \
settings.repaintingStart=8 \
settings.repaintingEnd=18 \
inputs.audio=https://assets.runware.ai/assets/inputs/a2be1c20-67e0-4321-8fc3-8a1fe2452b82.mp3{
"taskType": "audioInference",
"taskUUID": "a11d34e4-b519-4f10-be3c-e724ce1a7b79",
"model": "runware:ace-step@v1.5-xl-sft",
"positivePrompt": "Replace only the musical passage from 8 to 18 seconds with new content for a premium investigative maritime-insurance podcast bumper. Preserve the untouched audio before and after the replacement. Instead of the source's bowed-vibraphone melody, create a tense but understated interlocking figure using dry marimba, muted prepared piano, and a low plucked cello ostinato. Add tiny metallic accents reminiscent of drafting tools and cargo seals, treated as refined percussion rather than literal sound effects. Keep the existing tempo, pulse, tonal center, intimate studio acoustics, and restrained analog warmth. Enter seamlessly from the prepared-piano rhythm at 8 seconds, develop a memorable four-note question-and-answer motif, then simplify during the final two seconds so the passage reconnects naturally and invisibly with the original material at 18 seconds. Editorial, intelligent, meticulous, and modern; no vocals, speech, sea shanty references, waves, foghorns, EDM drops, trailer booms, or abrupt splice.",
"strength": 0.75,
"settings": {
"repaintingStart": 8,
"repaintingEnd": 18
},
"inputs": {
"audio": "https://assets.runware.ai/assets/inputs/a2be1c20-67e0-4321-8fc3-8a1fe2452b82.mp3"
}
}Response
{
"taskType": "audioInference",
"taskUUID": "a11d34e4-b519-4f10-be3c-e724ce1a7b79",
"audioUUID": "48b8b9ce-5bbf-4918-a2ed-563214057284",
"audioURL": "https://am.runware.ai/audio/os/a09dlim3/ws/5/ai/48b8b9ce-5bbf-4918-a2ed-563214057284.mp3",
"seed": 1559759902,
"cost": 0.0096
}