---
title: ACE-Step v1.5 XL Turbo | Runware Docs
url: https://runware.ai/docs/models/ace-step-v1-5-xl-turbo
description: Fast 4B music generation model with 8-step inference for higher-quality rapid iteration
---
# ACE-Step v1.5 XL Turbo

![ACE-Step v1.5 XL Turbo](https://assets.runware.ai/covers/ace-step-v1-5-xl-turbo.jpg)

ACE-Step v1.5 XL Turbo is the accelerated 4B DiT variant of ACE-Step 1.5. It is optimized for faster music generation with 8-step distilled inference while retaining the higher-capacity XL architecture. It supports text-to-music, cover generation, and repaint workflows, making it suitable for rapid iteration when the 2B turbo model is not enough in audio quality.

- **Status**: live
- **ID**: `runware:ace-step@v1.5-xl-turbo`
- Try in Playground
- **Release Date**: April 2, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Audio, Audio to Audio, Checkpoint

## Pricing

$0.00225 from, per run · ~12s per request

**Measured runs**

- duration 60 · steps 8: `$0.00225` (~4s)
- duration 30 · steps 8: `$0.00225` (~3s)
- duration 300 · steps 8: `$0.00675` (~11s)

**4 example generations**

- [text-to-audio](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo/examples#example-forensic-pollen-e-learning-song) · 60s: `$0.0009` (~12s)
- [audio-extend](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo/examples#example-wastewater-energy-narration-spot): `$0.00195` (~20s)
- [audio-repaint](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo/examples#example-rare-books-podcast-intro-segment): `$0.0039` (~22s)
- [audio-driven](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo/examples#example-heritage-crop-seed-vault-voiceover): `$0.0048` (~21s)

billed by compute time, so a request costs what it took · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

When `inputs.audio` is provided, `duration` cannot be used.

---

When `inputs.audio` is provided, `steps` must be at least `10`.

---

When `settings.repaintingStart` or `settings.repaintingEnd` is provided, `inputs.audio` is required.

---

When `strength` is provided, `inputs.audio` is required.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `audioInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

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

### [outputType](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Audio output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-outputformat)

- **Type**: `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**: `MP3` `WAV` `FLAC` `OGG`

### [audioSettings](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-audiosettings)

- **Path**: `audioSettings.bitrate`
- **Type**: `object (3 properties)`

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 |

> [!NOTE]
> **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.

#### [bitrate](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-audiosettings-bitrate)

- **Path**: `audioSettings.bitrate`
- **Type**: `integer`
- **Min**: `8`

Audio bitrate in kbps.

#### [channels](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-audiosettings-channels)

- **Path**: `audioSettings.channels`
- **Type**: `integer`
- **Default**: `2`

Number of audio channels. 1 for mono, 2 for stereo.

**Allowed values**: `1` `2`

#### [sampleRate](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-audiosettings-samplerate)

- **Path**: `audioSettings.sampleRate`
- **Type**: `integer`

Audio sample rate in Hz.

### [webhookURL](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses 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](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-uploadendpoint)

- **Type**: `string`
- **Format**: `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.

```text
// 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](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-numberresults)

- **Type**: `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.

### [audio](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-inputs-audio)

- **Path**: `inputs.audio`
- **Type**: `string`

Audio input (UUID or URL).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `runware:ace-step@v1.5-xl-turbo`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `3000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [duration](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-duration)

- **Type**: `float`
- **Min**: `30`
- **Max**: `300`
- **Step**: `0.1`
- **Default**: `60`

Length of the generated audio track in seconds.

### [seed](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-seed)

- **Type**: `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](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-steps)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `20`
- **Default**: `8`

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

**Learn more** (1 resource):

- [Steps](https://runware.ai/docs/learn/steps) (learn)

### [strength](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-strength)

- **Type**: `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):

- [Image To Image: Strength The Transformation Intensity](https://runware.ai/docs/learn/image-to-image#strength-the-transformation-intensity) (learn)
- [Image Inpainting: Strength Controlling Transformation Intensity](https://runware.ai/docs/learn/image-inpainting#strength-controlling-transformation-intensity) (learn)
- [Image Outpainting: Strength Understanding The Critical Threshold](https://runware.ai/docs/learn/image-outpainting#strength-understanding-the-critical-threshold) (learn)

**Settings**

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

### [bpm](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-settings-bpm)

- **Path**: `settings.bpm`
- **Type**: `integer`
- **Min**: `30`
- **Max**: `300`

Beats per minute. If not set, the model decides automatically.

### [keyScale](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-settings-keyscale)

- **Path**: `settings.keyScale`
- **Type**: `string`

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

### [lyrics](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-settings-lyrics)

- **Path**: `settings.lyrics`
- **Type**: `string`
- **Min**: `10`
- **Max**: `3000`

Song lyrics, typically formatted like a lyrics website.

### [repaintingEnd](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-settings-repaintingend)

- **Path**: `settings.repaintingEnd`
- **Type**: `float`
- **Min**: `0`
- **Max**: `300`

End time in seconds for repaint region. Requires input audio. Values beyond audio duration append new audio.

### [repaintingStart](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-settings-repaintingstart)

- **Path**: `settings.repaintingStart`
- **Type**: `float`
- **Min**: `-300`
- **Max**: `300`

Start time in seconds for repaint region. Requires input audio. Negative values prepend audio before the start.

### [timeSignature](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-settings-timesignature)

- **Path**: `settings.timeSignature`
- **Type**: `integer`

Beats per measure. If not set, the model decides automatically.

**Allowed values**: `2` `3` `4` `6`

### [vocalLanguage](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-settings-vocallanguage)

- **Path**: `settings.vocalLanguage`
- **Type**: `string`
- **Default**: `en`

ISO 639-1 language code for vocals. `unknown` for instrumental or auto detection.

**Allowed values**: `unknown` `ar` `az` `bg` `bn` `ca` `cs` `da` `de` `el` `en` `es` `fa` `fi` `fr` `he` `hi` `hr` `ht` `hu` `id` `is` `it` `ja` `ko` `la` `lt` `ms` `ne` `nl` `no` `pa` `pl` `pt` `ro` `ru` `sa` `sk` `sr` `sv` `sw` `ta` `te` `th` `tl` `tr` `uk` `ur` `vi` `yue` `zh`

**Features**

Standalone addons and post-processing features.

### [modularScheduler](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#request-advancedfeatures-modularscheduler)

- **Path**: `advancedFeatures.modularScheduler`
- **Type**: `object`

Manual scheduler configuration for fine-grained control over the diffusion process (sampler, modifiers, etc.).

## Response Parameters

### [taskType](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `audioInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [audioUUID](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#response-audiouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output audio.

### [audioURL](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#response-audiourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output audio.

### [audioBase64Data](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#response-audiobase64data)

- **Type**: `string`

Base64-encoded audio data.

### [audioDataURI](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#response-audiodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output audio.

### [seed](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#response-seed)

- **Type**: `integer`

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

### [cost](https://runware.ai/docs/models/ace-step-v1-5-xl-turbo#response-cost)

- **Type**: `float`

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

## Examples

### text-to-audio (text-to-audio)

[Listen to audio](https://assets.runware.ai/examples/ace-step-v1-5-xl-turbo/b8c99e38-8bfb-413e-84df-6dbd8e4bdfde.mp3)

```json
{
  "taskType": "audioInference",
  "taskUUID": "8edeea6f-6cbb-424c-b5cd-3024b5fb88f1",
  "model": "runware:ace-step@v1.5-xl-turbo",
  "positivePrompt": "Complete educational micro-song for a forensic science e-learning module about palynology. Warm, precise 1960s bossa nova with nylon-string guitar, brushed drum kit, upright bass, soft vibraphone, and brief clarinet responses. Calm, curious, academically credible mood rather than comic or childish. Clear English alto lead vocal with lightly spoken, highly intelligible verses and a memorable sung chorus; restrained backing harmonies only in the final chorus. Open with a two-bar guitar-and-vibraphone motif, move quickly through verse and chorus, add a short clarinet turnaround before verse two, then finish with a resolved final chorus and clean instrumental button. Keep the vocal forward in the mix and every technical term easy to understand. No sound effects, crowd noise, cinematic impacts, or long instrumental solo.",
  "duration": 60,
  "settings": {
    "lyrics": "[Verse 1]\nPollen rides on fabric, soil, and air,\nA microscopic trace collected with care.\nShape, pores, and surface patterns help reveal\nWhich plant left the grain upon the seal.\n\n[Chorus]\nCollect it clean, compare the scene,\nRead the grains that travel unseen.\nOne grain suggests; a group can show\nThe plants and places evidence may know.\n\n[Verse 2]\nUse sterile tools and package items dry,\nLabel every sample: where, when, and why.\nReference slides and seasonal records guide,\nBut context keeps conclusions qualified.\n\n[Final Chorus]\nCollect it clean, compare the scene,\nRead the grains that travel unseen.\nDocument the chain, let findings stay\nMeasured, repeatable, and clear all the way.",
    "bpm": 118,
    "keyScale": "C minor",
    "timeSignature": 4,
    "vocalLanguage": "en"
  }
}
```

---

### audio-driven (audio-driven)

[Listen to audio](https://assets.runware.ai/examples/ace-step-v1-5-xl-turbo/ea87bbe7-f93d-4db1-9ed0-0d6efef11eed.mp3)

```json
{
  "taskType": "audioInference",
  "taskUUID": "e40e5ef2-6e94-4649-8008-4ce11094f0bc",
  "model": "runware:ace-step@v1.5-xl-turbo",
  "positivePrompt": "Reimagine the entire source track as a premium narrated explainer for a regional heritage seed vault. Preserve its recognizable musical architecture: opening motif, phrase lengths, harmonic movement, sectional transitions, bridge placement, emotional peak, and resolved ending. Replace the original production with intimate chamber electronica built from felt piano, muted cello, glass marimba, soft seed-pod shakers, subtle modular pulses, bowed vibraphone, and a faint bed of field ambience suggesting wind through dry grain. The mood should feel quietly urgent, tactile, intelligent, and hopeful rather than sentimental. Keep the arrangement spacious beneath the words, then let the instruments gently bloom around the final message.\n\nFeature one warm, grounded adult female narrator speaking in clear natural English. This is voiceover, not singing, chanting, rapping, or theatrical character acting. Use measured documentary pacing, precise diction, restrained emotion, and short intentional pauses. Keep the voice centered, close, dry, and consistently intelligible above the music.\n\nNarration, spoken verbatim:\n\n“Most seeds are built to travel. Some are built to wait.\n\nInside regional seed libraries, rare beans, grains, and orchard varieties are dried, catalogued, and stored. When drought, disease, or changing seasons erase a crop from the field, its next chapter can begin from a labeled envelope.\n\nFarmers contribute seed. Researchers test resilience. Communities protect the plants shaped by their soil, their weather, and their stories.\n\nA seed vault is not a museum of what agriculture was. It is a working backup for what food can become.\n\nSupport your regional seed library—and help tomorrow take root.”\n\nAllow brief instrumental breaths between paragraphs. Finish with a soft cello resolution, the opening glass-marimba motif, and natural room decay.",
  "strength": 0.55,
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/8c309ce7-7737-4a9b-b5bb-88cce74869b2.mp3"
  }
}
```

---

### audio-repaint (audio-repaint)

[Listen to audio](https://assets.runware.ai/examples/ace-step-v1-5-xl-turbo/292bfe1f-7f26-422c-bd90-da06dc44ab38.mp3)

```json
{
  "taskType": "audioInference",
  "taskUUID": "9d8e3335-2c7a-4a68-b87c-a3cfe7408f03",
  "model": "runware:ace-step@v1.5-xl-turbo",
  "positivePrompt": "Replace only the designated internal section of the supplied podcast intro with a concise investigative chapter passage. Preserve the source track outside the repaint interval exactly. Match its tempo, key, room tone, analog warmth, dynamics, and chamber-jazz instrumentation so both edit boundaries feel musically invisible. Develop the established felt-piano motif into a more focused question-and-discovery phrase, answered by pizzicato cello and a brief bass-clarinet figure. Add delicate percussive details resembling a catalogue card being placed on a wooden desk, integrated rhythmically rather than as a literal sound effect. Keep brushed drums restrained and leave generous midrange space for host narration. The mood should suggest meticulous archival research, uncertain provenance, and an elegant auction-room atmosphere without becoming sinister. Build mild momentum through the middle of the replacement, then simplify the harmony and texture before the end boundary so it reconnects naturally to the untouched continuation. Instrumental only, no vocals, no spoken words, no dramatic trailer hits, and no abrupt change in loudness.",
  "strength": 0.7,
  "settings": {
    "repaintingStart": 8,
    "repaintingEnd": 20
  },
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/646e01e4-2cf7-46fb-ab73-c07c4890ac1d.mp3"
  }
}
```

---

### audio-extend (audio-extend)

[Listen to audio](https://assets.runware.ai/examples/ace-step-v1-5-xl-turbo/2664f2ea-a8b0-4bf0-910e-793cd159f46f.mp3)

```json
{
  "taskType": "audioInference",
  "taskUUID": "a138954c-8d5b-4d96-bcc1-6acf5042bd5b",
  "model": "runware:ace-step@v1.5-xl-turbo",
  "positivePrompt": "Continue naturally from the exact endpoint of the source track, preserving its rhythm, key, muted marimba, soft hand percussion, rounded bass, glass accents, subtle treatment-plant textures, warm documentary mix, and calm female narrator. Maintain the same measured delivery and public-service tone. The narrator continues verbatim: “That means fewer emissions, lower fuel costs, and a treatment plant that powers part of the city it serves. The next time a bus rolls past, some of its energy may have started beneath your street. Wastewater isn’t the end of the story. It’s where recovery begins.” Let the arrangement gently broaden beneath “powers part of the city,” then resolve after the final sentence with a concise marimba motif, warm sustained chord, and clean natural tail. Spoken narration only, not sung; clear intelligibility, no dramatic trailer effects, no abrupt transition.",
  "strength": 0.65,
  "settings": {
    "repaintingStart": 30,
    "repaintingEnd": 50
  },
  "inputs": {
    "audio": "https://assets.runware.ai/assets/inputs/d14a856b-29eb-4c52-bdeb-3e77ec533bb3.mp3"
  }
}
```