MireloMirelo SFX 2.0 (Video to Audio) API
Generate a soundtrack synced to your video with Mirelo SFX 2.0 — returns the audio track.
Params
Billed at this model’s published rate.
Result
Your generations will appear here
Other models from Mirelo
Same vendor, same API call — the differences are below.
| Model | Use case | Price | Resolution | Duration | Added |
|---|---|---|---|---|---|
| Mirelo SFX 2.0 (Text to Audio) | Text → Audio | No rate | — | 1–600s | Oct 2026 |
| Mirelo SFX 2.0 (Video to Video) | Video → Video | No rate | — | 1–600s | Oct 2026 |
Install the SDK
TypeScript targets Node 20+ and ships with types; Python needs 3.10+ and is async. Over REST there is nothing to install: call https://api.picsart.com from any HTTP client.
npm install @picsart/ai-sdkpip install picsart-ai-sdkAuthenticate
Send your Picsart API key as a bearer token. The SDK does it for you once the client is created.
import { createClient } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY, // sent as: Authorization: Bearer <key>
apiUrl: 'https://api.picsart.com',
});import os
from picsart_ai_sdk import create_client
ai = create_client(
api_key=os.environ["PICSART_API_KEY"], # sent as: Authorization: Bearer <key>
api_url="https://api.picsart.com",
)Authorization: Bearer <PICSART_API_KEY>Make a request
Call the model by its id. Over REST, one endpoint serves every model: POST /workflows/v1/models/execute with the model id and its input in the body. The outer params is the envelope every workflow takes; the inner one is this model's input, with the same names generate() takes.
import { createClient } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.picsart.com',
});
const result = await ai.generate('mirelo-sfx-2.0-video-to-audio', {
videoUrl: "https://cdn.example.com/input.mp4",
prompt: "A serene mountain lake at golden hour, ultra detailed",
duration: 10
});
console.log(result.url); // audio URLimport asyncio
import os
from picsart_ai_sdk import create_client
async def main() -> None:
async with create_client(
api_key=os.environ["PICSART_API_KEY"],
api_url="https://api.picsart.com",
) as ai:
result = await ai.generate("mirelo-sfx-2.0-video-to-audio", {
"videoUrl": "https://cdn.example.com/input.mp4",
"prompt": "A serene mountain lake at golden hour, ultra detailed",
"duration": 10,
})
print(result.url) # audio URL
asyncio.run(main())curl -X POST 'https://api.picsart.com/workflows/v1/models/execute' \
-H 'Authorization: Bearer $PICSART_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"params": {
"model": "mirelo-sfx-2.0-video-to-audio",
"params": {
"videoUrl": "https://cdn.example.com/input.mp4",
"prompt": "A serene mountain lake at golden hour, ultra detailed",
"duration": 10
}
}
}'Async (submit & poll)
This model can run longer than the sync limit (~20s). generate() waits for you; to hold on to the job instead, submit it and poll. Over REST, send it to /workflows/v1/models/submit and poll /workflows/v1/models/{taskId}/result until response.status is COMPLETED or FAILED.
import { createClient } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.picsart.com',
});
// Returns the generation id at once — store it to pick the job up later.
const generationId = await ai.submit('mirelo-sfx-2.0-video-to-audio', {
videoUrl: "https://cdn.example.com/input.mp4",
prompt: "A serene mountain lake at golden hour, ultra detailed",
duration: 10
});
// Polls until the job completes; throws if it fails or is cancelled.
const result = await ai.result('mirelo-sfx-2.0-video-to-audio', generationId);
console.log(result.url); // audio URLimport asyncio
import os
from picsart_ai_sdk import create_client
async def main() -> None:
async with create_client(
api_key=os.environ["PICSART_API_KEY"],
api_url="https://api.picsart.com",
) as ai:
# Returns the generation id at once — store it to pick the job up later.
generation_id = await ai.submit("mirelo-sfx-2.0-video-to-audio", {
"videoUrl": "https://cdn.example.com/input.mp4",
"prompt": "A serene mountain lake at golden hour, ultra detailed",
"duration": 10,
})
# Polls until the job completes; raises ApiError if it fails or is cancelled.
result = await ai.result("mirelo-sfx-2.0-video-to-audio", generation_id)
print(result.url) # audio URL
asyncio.run(main())# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/v1/models/submit' \
-H 'Authorization: Bearer $PICSART_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"params": {
"model": "mirelo-sfx-2.0-video-to-audio",
"params": {
"videoUrl": "https://cdn.example.com/input.mp4",
"prompt": "A serene mountain lake at golden hour, ultra detailed",
"duration": 10
}
}
}'
# → { "status": "success", "response": { "id": "task_abc123" } }
# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/v1/models/task_abc123/result' \
-H 'Authorization: Bearer $PICSART_API_KEY'Parameters
9 parameters, the same for the SDK and for the inner params over REST. Required ones must be supplied; the rest fall back to their defaults.
| Parameter | Type | Required | Default | Details |
|---|---|---|---|---|
videoUrlThe video to work on, as a URL. | file (video) | yes | — | — |
promptThe text to speak. For music and sound effects, what to make, in plain language. | text | no | — | max 2000 chars |
negativePromptWhat to keep out of the result, such as text, watermarks or blur. | text | no | — | max 1000 chars |
preserveSpeechKeep the speech in the source audio unchanged. | boolean | no | true | — |
durationLength of the output, in seconds. | range | no | 10 | 1–600 (step 1) |
countHow many results to make in one call. Each one is charged. | enum | no | 2 | 1, 2, 3, 4 |
formatFile format of the result. | enum | no | wav | wav, mp3, aac, flac |
bitrateKbpsBitrate of the audio, in kbps. | range | no | — | 32–320 (step 1) |
seedSeed for the random generator. The same seed and inputs repeat a result; leave it out for a random one. | range | no | — | 0–2147483647 (step 1) |
Response
generate() resolves once the job completes. An audio URL. Over REST the output is at response.result, inside the gateway's status envelope with the task id, its status and the amount charged.
{
"items": [
{
"url": "https://cdn.picsart.com/…/result"
}
],
"model": "mirelo-sfx-2.0-video-to-audio"
}{
"status": "success",
"response": {
"id": "task_abc123",
"status": "COMPLETED",
"result": {
"url": "https://cdn.picsart.com/…/result",
"items": [
{
"url": "https://cdn.picsart.com/…/result"
}
],
"model": "mirelo-sfx-2.0-video-to-audio"
}
}
}Overview
Alongside the unified model APIs, we expose compatibility APIs that take each vendor's original parameters exactly as the vendor defines them — nothing renamed, nothing reshaped on the way through.
That makes them the shortest path onto Picsart if you already work with the vendor directly: the request bodies you've already written keep working as they are. You keep their parameter names and defaults, and you get the vendor's full parameter set rather than the subset that is shared across every model.
The cost is that a request is written for one vendor — switching models later means rewriting it, and results come back in the vendor's own shape. When you'd rather write once and change models freely, use the unified API.
Make a request
Call the workflow with ai.apis.run() in TypeScript or Python, or hit /workflows/{workflow}/execute directly — params is passed through untouched either way.
These endpoints are addressed by workflow name rather than model id: the one in this model's header, since one model runs as one workflow. Authentication is unchanged — your Picsart API key as a bearer token (see Authentication).
import { createClient, ApiRunMode } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.picsart.com',
});
// Calls the 'mirelo-ai/sfx2.0/video-to-audio' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('mirelo-ai/sfx2.0/video-to-audio', {
video_url: "https://di3otfzjg1gxa.cloudfront.net/chase.mp4",
text_prompt: "Distant police sirens, tires screeching on asphalt"
}, {
mode: ApiRunMode.SYNC,
});
console.log(result); // workflow-specific output
console.log(usage?.credits); // amount charged, in $import asyncio
import os
from picsart_ai_sdk import ApiRunMode, create_client
async def main() -> None:
async with create_client(
api_key=os.environ["PICSART_API_KEY"],
api_url="https://api.picsart.com",
) as ai:
# Calls the 'mirelo-ai/sfx2.0/video-to-audio' workflow directly — params are sent as-is.
response = await ai.apis.run("mirelo-ai/sfx2.0/video-to-audio", {
"video_url": "https://di3otfzjg1gxa.cloudfront.net/chase.mp4",
"text_prompt": "Distant police sirens, tires screeching on asphalt",
}, mode=ApiRunMode.SYNC)
print(response["result"]) # workflow-specific output
print((response.get("usage") or {}).get("credits")) # amount charged, in $
asyncio.run(main())curl -X POST 'https://api.picsart.com/workflows/mirelo-ai/sfx2.0/video-to-audio/execute' \
-H 'Authorization: Bearer $PICSART_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"params": {
"video_url": "https://di3otfzjg1gxa.cloudfront.net/chase.mp4",
"text_prompt": "Distant police sirens, tires screeching on asphalt"
}
}'Async (submit & poll)
This model can run longer than the sync limit (~20s). In the SDK, ai.apis.run() with ApiRunMode.ASYNC polls for you; over HTTP, submit and poll yourself.
import { createClient, ApiRunMode } from '@picsart/ai-sdk';
const ai = createClient({
apiKey: process.env.PICSART_API_KEY,
apiUrl: 'https://api.picsart.com',
});
// mode: ASYNC submits the job and polls under the hood — you just await.
const { result } = await ai.apis.run('mirelo-ai/sfx2.0/video-to-audio', {
video_url: "https://di3otfzjg1gxa.cloudfront.net/chase.mp4",
text_prompt: "Distant police sirens, tires screeching on asphalt"
}, {
mode: ApiRunMode.ASYNC,
});
console.log(result);import asyncio
import os
from picsart_ai_sdk import ApiRunMode, create_client
async def main() -> None:
async with create_client(
api_key=os.environ["PICSART_API_KEY"],
api_url="https://api.picsart.com",
) as ai:
# mode=ASYNC submits the job and polls under the hood — you just await.
response = await ai.apis.run("mirelo-ai/sfx2.0/video-to-audio", {
"video_url": "https://di3otfzjg1gxa.cloudfront.net/chase.mp4",
"text_prompt": "Distant police sirens, tires screeching on asphalt",
}, mode=ApiRunMode.ASYNC)
print(response["result"])
asyncio.run(main())# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/mirelo-ai/sfx2.0/video-to-audio/submit' \
-H 'Authorization: Bearer $PICSART_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"params": {
"video_url": "https://di3otfzjg1gxa.cloudfront.net/chase.mp4",
"text_prompt": "Distant police sirens, tires screeching on asphalt"
}
}'
# → { "status": "success", "response": { "id": "wf_abc123" } }
# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/mirelo-ai/sfx2.0/video-to-audio/wf_abc123/result' \
-H 'Authorization: Bearer $PICSART_API_KEY'Parameters
11 parameters, sent inside params. These are the vendor's own names, so they line up one-for-one with the vendor's documentation. Required ones must be supplied; the rest fall back to their defaults.
| Parameter | Type | Required | Default | Details |
|---|---|---|---|---|
return_speechAlso return the input's separated speech as its own audio file, in the response's speech. With preserve_speech false the soundtracks are sound effects only and the speech is separated while they generate. With preserve_speech true it is the speech separated from the input that the soundtracks were generated around, not the speech in them: the model renders that speech anew, so the file does not cancel or double it cleanly when layered onto a soundtrack. The file is mono, in upload_audio_format, and as long as the soundtracks. It is not billed. | boolean | no | false | — |
durationSeconds of sound to generate, from 1 s to 600 s, clamped to the video's length. Over 10 s generates in 10 s windows. A video shorter than 1 s answers 400. | number | no | 10 | 1–600 |
preserve_speechKeep the speech in the input's audio and generate the rest of the soundtrack around it. False generates sound effects only and suppresses speech. | boolean | no | true | — |
seedSeed for generation. -1 or None for random. | integer | no | — | -1–18446744073709552000 |
video_urlVideo to add sound to: an http(s) URL, or a base64 data URI up to 8 MB. | string | yes | — | e.g. https://di3otfzjg1gxa.cloudfront.net/chase.mp4 |
text_promptOptional text guiding the soundtrack. Name sounds the picture does not show, such as off-screen sounds or an ambience bed, to have them worked into it. | string | no | — | max 2000 chars e.g. Distant police sirens, tires screeching on asphalt |
upload_audio_formatAudio format of each file | string | no | wav | wavmp3aacflac |
upload_audio_bitrate_kbpsBitrate in kbps for an mp3 or aac upload. mp3 is written at exactly this constant rate, one of 32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, 320. aac takes 32 to 256 as a target the encoder may undershoot on mono or sparse audio. Unset keeps the default: mp3 at LAME V0 VBR, aac at a 256 kbps target. Refused with a lossless upload_audio_format. | integer | no | — | 32–320 |
negative_promptSounds to keep out of the result, as a short comma-separated list. | string | no | — | max 1000 chars e.g. music, crowd noise |
num_samplesNumber of variations to generate. Billed per sample. | integer | no | 2 | 1–4 |
optionsPlatform-specific options for safety checks and Picsart Drive integration. | object | no | — | — |
└ safety_checksSafety check configuration. | object | no | — | — |
└ enabledEnable or disable text safety checks. Defaults to true. | boolean | no | true | — |
└ drivePicsart Drive storage options. When provided, the result will be saved to the user's Drive. | object | no | — | — |
└ nameFilename to save the result as in Picsart Drive. | string | yes | — | — |
└ attributesAdditional file metadata attributes. | object | no | — | — |
└ folderDestination folder in Picsart Drive. | object | no | — | — |
Response
Over HTTP the output arrives inside a status envelope, at response.result. ai.apis.run() unwraps that envelope for you and resolves to { result, usage } instead. Either way the result itself is the vendor's own shape.
{
"result": {
"audio": [
{
"file_name": "generated_audio_1.wav",
"content_type": "audio/wav",
"url": "https://di3otfzjg1gxa.cloudfront.net/chase_output_1.wav"
}
],
"model": "sfx-2.0",
"speech": {
"windows_failed": 0,
"outcome": "speech",
"audio": {
"file_size": 4404019,
"file_name": "z9RV14K95DvU.png",
"content_type": "image/png",
"url": "https://cdn.picsart.com/…/result.mp3"
},
"windows": 0,
"windows_with_speech": 0
}
}
}{
"status": "success",
"response": {
"id": "wf_abc123",
"status": "COMPLETED",
"result": {
"audio": [
{
"file_name": "generated_audio_1.wav",
"content_type": "audio/wav",
"url": "https://di3otfzjg1gxa.cloudfront.net/chase_output_1.wav"
}
],
"model": "sfx-2.0",
"speech": {
"windows_failed": 0,
"outcome": "speech",
"audio": {
"file_size": 4404019,
"file_name": "z9RV14K95DvU.png",
"content_type": "image/png",
"url": "https://cdn.picsart.com/…/result.mp3"
},
"windows": 0,
"windows_with_speech": 0
}
}
}
}Rates
What this model costs per generation, in USD. Every row is an exact rate — the columns are the settings that change it.