MODEL ID runware:ace-step@v1.5-turbo

live

ACE-Step v1.5 Turbo

January 1, 2026

ACE-Step v1.5 Turbo is a speed-optimized variant of the ACE-Step v1.5 music generation model. It delivers faster inference with fewer denoising steps while retaining the core capabilities of the Base model, including voice cloning, lyric editing, remixing, and multilingual support across 50+ languages.

API Options

Platform-level options for task execution and delivery.

taskType string required value: audioInference: Identifier for the type of task being performed

taskUUID string required UUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType string default: URL: Audio output type.

Allowed values 3 values

outputFormat string default: MP3

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

`MP3`: Compressed audio, smaller file size.
`WAV`: Uncompressed, high-quality audio.
`FLAC`: Lossless compression.
`OGG`: Open-source compressed audio format (Vorbis codec).

Allowed values 4 values

audioSettings object

Audio encoding settings for controlling the bitrate, number of channels, and sample rate of the generated audio. Only applicable for lossy output formats (MP3 and OGG). When using lossless formats (WAV or FLAC), this parameter must not be provided.

The available sample rates and valid bitrate ranges depend on the output format. For OGG, bitrate limits also vary by the number of channels.

MP3 bitrate limits

Bitrate limits for MP3 are the same regardless of mono or stereo.

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	8 kbps	64 kbps
11,025 Hz	8 kbps	64 kbps
12,000 Hz	8 kbps	64 kbps
16,000 Hz	8 kbps	160 kbps
22,050 Hz	8 kbps	160 kbps
24,000 Hz	8 kbps	160 kbps
32,000 Hz	32 kbps	320 kbps
44,100 Hz	32 kbps	320 kbps
48,000 Hz	32 kbps	320 kbps

OGG bitrate limits — Mono (1 channel)

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	8 kbps	40 kbps
12,000 Hz	16 kbps	48 kbps
16,000 Hz	16 kbps	96 kbps
24,000 Hz	16 kbps	80 kbps
48,000 Hz	32 kbps	224 kbps

OGG bitrate limits — Stereo (2 channels)

Sample Rate	Min Bitrate	Max Bitrate
8,000 Hz	16 kbps	80 kbps
12,000 Hz	16 kbps	96 kbps
16,000 Hz	24 kbps	192 kbps
24,000 Hz	32 kbps	160 kbps
48,000 Hz	48 kbps	256 kbps

Lossless formats: When outputFormat is set to WAV or FLAC, the audioSettings parameter is not available since these formats produce uncompressed or lossless audio with no configurable encoding settings.

Properties 3 properties

audioSettings » bitrate bitrate integer min: 8: Audio bitrate in kbps.

audioSettings » channels channels integer default: 2: Number of audio channels. 1 for mono, 2 for stereo.

Allowed values 2 values

audioSettings » sampleRate sampleRate integer: Audio sample rate in Hz.

webhookURL string URI

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Learn more 1 resource

Webhooks
PLATFORM

deliveryMethod string default: sync

Determines how the API delivers task results.

Allowed values 2 values

: Returns complete results directly in the API response.
: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string URI

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

ttl integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults integer min: 1 max: 4 default: 1: Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

Inputs

Input resources for the task (images, audio, etc). These must be nested inside the inputs object.

inputs » audio audio string: Audio input (UUID or URL).

Generation Parameters

Core parameters for controlling the generated content.

model string required value: runware:ace-step@v1.5-turbo

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string required min: 2 max: 3000

Text prompt describing elements to include in the generated output.

Learn more 2 resources

negativePrompt string min: 2 max: 3000

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

Learn more 1 resource

Text To Image: Prompts Guiding The Generation
GUIDE

duration float min: 6 max: 300 step: 0.1 default: 60: Length of the generated audio track in seconds.

seed integer min: 0 max: 2147483647: Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

steps integer min: 1 max: 20 default: 10

Total number of denoising steps. Higher values generally produce more detailed results but take longer.

Learn more 1 resource

Text To Image: Steps Trading Quality For Speed
GUIDE

CFGScale float min: 1 max: 30 step: 0.01 default: 10

Guidance scale. Higher values follow the prompt more closely at the cost of quality.

Learn more 1 resource

Text To Image: Cfg Scale Balancing Creativity And Control
GUIDE

strength float min: 0 max: 1 step: 0.01 default: 0.5

Fraction of steps using the input source instead of generated output.

Learn more 3 resources

Settings

Technical parameters to fine-tune the inference process. These must be nested inside the settings object.

settings » bpm bpm integer min: 30 max: 300: Beats per minute. If not set, the model decides automatically.

settings » coverConditioningScale coverConditioningScale float min: 0 max: 1 step: 0.01 default: 1: Fraction of steps using source-audio conditioning.

settings » guidanceType guidanceType string default: apg

Controls how guidance is applied during generation.

Allowed values 2 values

: Adaptive Projected Guidance.
: Classifier-Free Guidance.

settings » keyScale keyScale string: Musical key and scale in '{Note}{Accidental} {Mode}' format (e.g. 'C major', 'F# minor', 'Bb major').

settings » lyrics lyrics string min: 10 max: 3000 default:: Song lyrics, typically formatted like a lyrics website.

settings » repaintingEnd repaintingEnd float min: 0 max: 300: End time in seconds for repaint region. Requires input audio. Values beyond audio duration append new audio.

settings » repaintingStart repaintingStart float min: -300 max: 300: Start time in seconds for repaint region. Requires input audio. Negative values prepend audio before the start.

settings » timeSignature timeSignature string: Beats per measure. Empty string lets the model decide.

Allowed values 4 values

settings » vocalLanguage vocalLanguage string default: en: ISO 639-1 language code for vocals. unknown for instrumental or auto detection.

Allowed values 51 values

taskType string required value: audioInference: Type of the task.

taskUUID string required UUID v4: UUID of the task.

audioUUID string required UUID v4: UUID of the output audio.

audioURL string URI: URL of the output audio.

audioBase64Data string: Base64-encoded audio data.

audioDataURI string URI: Data URI of the output audio.

seed integer: The seed used for generation. If none was provided, shows the randomly generated seed.

cost float: Task cost in USD. Present when includeCost is set to true in the request.

Text to Audio

Midnight Roller Rink Anthem

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "f5a96b26-ba23-4d8b-bbec-ee0c117a6e7e",
  "model": "runware:ace-step@v1.5-turbo",
  "positivePrompt": "An energetic retro-funk pop song set in a glowing roller rink, with punchy bass, crisp handclaps, sparkling synth leads, rhythmic guitar chops, and a confident female vocal. The mood is playful, nostalgic, and triumphant, like a late-night skate session turning into a personal victory soundtrack. Clean commercial production, memorable chorus, danceable groove, rich backing vocals, and a bright polished mix.",
  "negativePrompt": "muddy mix, distorted vocals, harsh treble, slow ballad, orchestral score, heavy metal, spoken word, low energy, chaotic structure, noisy percussion",
  "duration": 42,
  "seed": 2249,
  "steps": 8,
  "CFGScale": 7.5,
  "settings": {
    "bpm": 116,
    "guidanceType": "apg",
    "keyScale": "A minor",
    "timeSignature": 4,
    "vocalLanguage": "en",
    "lyrics": "[Verse]\nWheels on the maple, sparks in a line\nNeon on my jacket, keeping perfect time\nUsed to hide in corners, laces tied too tight\nNow I trace a silver signature across the floor tonight\n\n[Pre-Chorus]\nHeartbeat in the speakers, rising with the crowd\nEvery little doubt is fading out loud\n\n[Chorus]\nSpin me through the midnight, let the colors blur\nI was built for this, and now I'm sure\nRound and round the rhythm, shining at my own command\nUnder disco halos, I can finally stand\n\n[Verse]\nMirror ball confessions written in the air\nFriends along the guardrail throwing laughter everywhere\nEvery turn a promise, every glide a flame\nI came in feeling invisible, I leave them knowing my name\n\n[Chorus]\nSpin me through the midnight, let the colors blur\nI was built for this, and now I'm sure\nRound and round the rhythm, shining at my own command\nUnder disco halos, I can finally stand\n\n[Outro]\nKeep the wheels rolling, keep the floor alive\nPast the closing music, watch me thrive"
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "f5a96b26-ba23-4d8b-bbec-ee0c117a6e7e",
  "audioUUID": "641baa00-5371-4e38-9df1-f835a161de82",
  "audioURL": "https://am.runware.ai/audio/os/a25d05/ws/5/ai/641baa00-5371-4e38-9df1-f835a161de82.mp3",
  "seed": 2249,
  "cost": 0.0006
}

Text to Audio

Velvet Night Train Ballad

0:00

Request

{
  "taskType": "audioInference",
  "taskUUID": "b0996821-7a9f-4add-8ca6-e0b7be9de73e",
  "model": "runware:ace-step@v1.5-turbo",
  "positivePrompt": "A sleek retro-pop ballad with pulsing analog synths, warm electric piano, soft drum machine, fretless bass, and expressive female vocals. The mood is intimate, nocturnal, and wistful, like watching towns blur past from a sleeper train window at 2 a.m. Polished production, catchy chorus, rich harmonies, subtle tape texture, and a memorable melodic hook.",
  "negativePrompt": "heavy metal guitars, aggressive rap delivery, distorted screaming, chaotic percussion, crowd noise, lo-fi muddiness, glitch overload, comedic tone",
  "duration": 42,
  "seed": 32295,
  "steps": 8,
  "CFGScale": 8,
  "settings": {
    "bpm": 96,
    "guidanceType": "apg",
    "keyScale": "F# minor",
    "timeSignature": 4,
    "vocalLanguage": "en",
    "lyrics": "[Verse]\nSilver stations drift away\nNames dissolve in window gray\nTicket stubs and fading light\nFold into the velvet night\n\n[Pre-Chorus]\nEvery mile rewrites the air\nYou were almost with me there\n\n[Chorus]\nRide with me through the sleeping wire\nThrough the hum and the fading fire\nIf dawn arrives before we do\nLeave your echo in the blue\nRide with me, don’t say goodbye\nBe the spark behind my eye\nWhen the last red signal falls\nI will hear you through it all\n\n[Verse]\nCoffee cooling in my hand\nUnknown rivers cross the land\nQuiet neon, distant yards\nLittle halos, passing sparks\n\n[Chorus]\nRide with me through the sleeping wire\nThrough the hum and the fading fire\nIf dawn arrives before we do\nLeave your echo in the blue"
  }
}

Response

{
  "taskType": "audioInference",
  "taskUUID": "b0996821-7a9f-4add-8ca6-e0b7be9de73e",
  "audioUUID": "43e99b46-965c-4116-8914-d1726e115b33",
  "audioURL": "https://am.runware.ai/audio/os/a21d05/ws/5/ai/43e99b46-965c-4116-8914-d1726e115b33.mp3",
  "seed": 32295,
  "cost": 0.0006
}