Mirelo SFX 2.0 Video-to-Audio API on WaveSpeedAI

Name: Mirelo SFX 2.0 Video-to-Audio
Brand: mirelo-ai
SKU: mirelo-ai/sfx-2.0/video-to-audio
Price: 0.016 USD
Availability: InStock

README

Mirelo SFX 2.0 Video-to-Audio

Mirelo SFX 2.0 Video-to-Audio generates sound effects and ambience synchronized with the action in an input video, then returns the result as a standalone audio track. Use optional text guidance to describe the desired soundtrack, add a negative prompt to exclude unwanted sounds, and preserve existing speech when dialogue should remain.

Unlike video-to-video sound generation, this endpoint returns audio only, making it useful when you want to continue mixing, replacing, or editing the soundtrack separately from the original footage.

Why Choose This?

Video-synchronized sound generation
Generate sound effects and ambience that follow the action and timing of the source video.
Prompt-guided sound design
Describe the sounds, environment, intensity, and atmosphere you want to hear.
Negative prompt control
Specify unwanted sounds, voices, music, or other audio elements to avoid.
Speech preservation
Keep existing speech while generating a new surrounding soundscape.
Up to 10 minutes
Request generated audio from 1 to 600 seconds.
Multiple audio formats
Export the generated soundtrack as wav, mp3, aac, or flac.
Standalone audio output
Receive the generated soundtrack separately without re-rendering the source video.

Parameters

Parameter	Required	Description
video	Yes	Input video URL used to guide sound generation. The source video must be at least `1` second long.
prompt	No	Optional description of the desired soundtrack, sound effects, environment, or audio direction. Maximum `2000` characters.
negative_prompt	No	Optional description of sounds or elements to avoid. Maximum `1000` characters.
preserve_speech	No	Preserve existing speech while generating other sounds around it. Default: `true`.
duration	No	Requested audio duration in seconds. Range: `1–600`. Default: `10`. Generation cannot continue beyond the source video length.
audio_bitrate_kbps	No	Optional target bitrate for MP3 or AAC output. Omit for automatic encoding.
output_format	No	Output audio format: `wav`, `mp3`, `aac`, or `flac`. Default: `wav`.
seed	No	Optional integer seed from `0` to `2147483647`. Omit for random generation.

How to Use

Provide a source video — Upload a video or supply its URL.
Add sound guidance optional — Use prompt to describe the desired effects, ambience, and soundtrack direction.
Add exclusions optional — Use negative_prompt to describe sounds that should be avoided.
Configure speech preservation — Keep preserve_speech=true when existing dialogue should remain.
Set duration — Choose the requested audio length from 1 to 600 seconds.
Choose output format — Select wav, mp3, aac, or flac.
Set bitrate optional — Configure bitrate when using MP3 or AAC.
Set seed optional — Use a fixed seed when reproducibility is needed.
Submit — Generate and retrieve the synchronized audio track.

Pricing

Pricing is based on the requested duration.

The rate is $0.016 per requested second.

Duration	Price
1s	$0.016
5s	$0.080
10s	$0.160
30s	$0.480
60s	$0.960
600s	$9.600

Billing uses the requested duration.

If the source video is shorter than the requested duration, sound generation stops at the end of the source video, but billing still uses the requested duration. Set duration no longer than the source clip when you do not need additional requested time.

Best Use Cases

Film and cinematic sound design — Generate effects and ambience synchronized with visual action.
Gameplay audio — Add impacts, movement, environmental sounds, and other effects to gameplay footage.
Product videos — Create synchronized interactions, mechanical sounds, and environmental audio for demonstrations.
Social content — Add sound design to short-form visual content before final editing.
Foley-style workflows — Generate footsteps, object handling, movement, impacts, and other action-driven sounds.
Soundtrack prototyping — Explore alternative sound directions while keeping the source video untouched.
Post-production — Generate a standalone synchronized audio track for further mixing and editing.

Pro Tips

Describe concrete sound sources, timing, movement, intensity, and environment.
Explain how sounds should correspond to visible actions when synchronization matters.
Use negative_prompt to reduce unwanted music, speech, voices, or background sounds.
Keep preserve_speech=true when dialogue from the source should remain in the generated audio.
Set preserve_speech=false when you want the generated track focused on sound effects without preserving source speech.
Match duration to the usable length of the source video to avoid paying for requested time beyond the available footage.
Start with shorter generations when testing a new sound direction.
Use wav or flac when lossless output is preferred.

Notes

video is required.
The input video must be at least 1 second long.
duration supports 1–600 seconds and defaults to 10.
Sound generation cannot continue beyond the source video length.
Billing still uses the requested duration when it exceeds the available source-video duration.
preserve_speech defaults to true.
preserve_speech=true preserves existing speech, not all original background audio.
Generation longer than 10 seconds is processed in consecutive windows.
output_format defaults to wav.
Leave audio_bitrate_kbps empty for WAV and FLAC.
MP3 supports 32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, or 320 kbps.
AAC accepts an integer target bitrate from 32 to 256 kbps; actual encoded bitrate may be lower.
When no bitrate is specified, MP3 uses variable bitrate and AAC uses a 256 kbps target.

Related Models

Mirelo SFX 2.0 Text-to-Audio — Generate sound effects and ambience directly from text descriptions.
Mirelo SFX 2.0 Video-to-Audio — Generate synchronized standalone audio from an input video.
Mirelo SFX 2.0 Video-to-Video — Add synchronized generated sound effects to an existing video and return the completed video.

Sfx 2.0 Video To Audio API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/mirelo-ai/sfx-2.0/video-to-audio with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Sfx 2.0 Video To Audio below.

HTTP example

set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "preserve_speech": true,
    "duration": 10,
    "output_format": "wav"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/mirelo-ai/sfx-2.0/video-to-audio" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Node.js example

const submitUrl = "https://api.wavespeed.ai/api/v3/mirelo-ai/sfx-2.0/video-to-audio";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "preserve_speech": true,
        "duration": 10,
        "output_format": "wav"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}

Python example

import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "preserve_speech": True,
    "duration": 10,
    "output_format": "wav"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/mirelo-ai/sfx-2.0/video-to-audio", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Sfx 2.0 Video To Audio API — Frequently asked questions

What is the Sfx 2.0 Video To Audio API?

Sfx 2.0 Video To Audio is a Mirelo Ai model for sound effect generation, exposed as a REST API on WaveSpeedAI. Mirelo SFX 2.0 Video-to-Audio generates synchronized sound effects from input videos and returns standalone audio tracks, enabling editors to add sound design without re-rendering the source video for film, social content, games, ads, and post-production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Sfx 2.0 Video To Audio API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/mirelo-ai/mirelo-ai-sfx-2.0-video-to-audio.

How much does Sfx 2.0 Video To Audio cost per run?

Sfx 2.0 Video To Audio starts at $0.016 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Sfx 2.0 Video To Audio accept?

Key inputs: `prompt`, `video`, `duration`, `seed`, `negative_prompt`, `audio_bitrate_kbps`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/mirelo-ai/mirelo-ai-sfx-2.0-video-to-audio.

How do I get started with the Sfx 2.0 Video To Audio API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Sfx 2.0 Video To Audio outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Mirelo Ai). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

mirelo-ai/sfx-2.0/video-to-audio

ExamplesView all

Related Models

README

Mirelo SFX 2.0 Video-to-Audio

Why Choose This?

Parameters

How to Use

Pricing

Best Use Cases

Pro Tips

Notes

Related Models

Sfx 2.0 Video To Audio API — Quick start

Sfx 2.0 Video To Audio API — Frequently asked questions

More from Mirelo Ai

More Sound Effects Generation models