Seedream 5.0 Pro is LIVE | Try in Image Generator →
Home/Explore/Sonilo/V1/Video To Video Sound

Sonilo Video to Video Sound

sonilo /

Sonilo Video to Video Sound adds generated music and sound effects to input videos, creating one or more videos with new audio tracks for video sound design, soundtrack generation, ads, social content, and creative production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

video-dubbing
Input

Idle

$0.018per run·~55 / $1

ExamplesView all

Related Models

README

Sonilo Video-to-Video Sound

Sonilo Video-to-Video Sound creates a complete video soundtrack from generated music and sound effects, then returns an MP4 video with the new audio track. Upload a video, describe the desired music and sound effects, optionally define time-aligned SFX segments, and generate a finished video with synchronized audio.

Why Choose This?

  • Video-to-video soundtrack generation
    Generate music and sound effects for an input video, then package them into a final MP4 output.

  • Music and SFX control
    Use music_prompt for the generated music direction and sfx_prompt for the overall sound-effect style.

  • Time-aligned sound segments
    Use segments to define sound effects for specific moments in the video.

  • Speech preservation option
    Enable preserve_speech when the original speech from the input video should remain.

  • Audio ducking support
    Use ducking to lower generated music and sound effects while speech is present.

  • Standard video output
    The final MP4 video is returned as a URL in the standard WaveSpeed prediction response.

Parameters

ParameterRequiredDescription
videoYesInput video. Maximum duration: 180 seconds. Maximum file size: 300 MB.
music_promptNoOptional prompt describing the generated music. Maximum length: 2,000 characters.
sfx_promptNoOptional overall prompt describing the generated sound effects. Maximum length: 2,000 characters.
segmentsYesTime-aligned sound-effect prompts. Each item includes start, end, and prompt. Provide 1 to 30 segments.
preserve_speechNoPreserve speech from the input video. When enabled, ducking is ignored.
duckingNoLower generated music and sound effects while speech is present.

Segments

Use segments when specific parts of the video need different sound effects.

Each segment contains:

FieldDescription
startSegment start time in seconds.
endSegment end time in seconds.
promptSound-effect prompt for this segment.

The first segment must start at 0. Adjacent segments must be continuous without gaps or overlap, and the final segment cannot exceed the source video duration.

How to Use

  1. Upload your video — Provide the input video that needs a generated soundtrack.
  2. Add music prompt optional — Describe the desired music style, mood, genre, tempo, or instrumentation.
  3. Add SFX prompt optional — Describe the overall sound-effect style, ambience, realism, or intensity.
  4. Add segments — Define time-aligned sound-effect prompts for specific moments in the video.
  5. Configure speech handling optional — Enable preserve_speech if the original speech should remain.
  6. Configure ducking optional — Use ducking to reduce generated audio while speech is present.
  7. Submit — Generate the final MP4 video with the new audio track.

Pricing

Pricing is $0.018 per second of input video duration. Billing duration is rounded up to the next whole second and capped at 180 seconds.

Video DurationPrice
1s$0.018
10s$0.18
60s$1.08
180s$3.24

Best Use Cases

  • Full video soundtracks — Generate music and sound effects together for a complete video output.
  • Social video production — Add synchronized audio to reels, shorts, ads, and campaign videos.
  • Cinematic sound design — Create music, ambience, and action-based sound effects for visual scenes.
  • Speech-aware soundtrack generation — Preserve original speech while adding generated background music and effects.
  • Segment-based SFX control — Assign different sound effects to different moments in the video.
  • Creative prototyping — Test music and sound design directions before final audio production.

Pro Tips

  • Use music_prompt to describe genre, mood, tempo, instruments, and production style.
  • Use sfx_prompt to describe the overall ambience, realism, intensity, or sound palette.
  • Use segments when different moments need different sound effects.
  • Keep segment prompts short, concrete, and tied to visible action.
  • Enable preserve_speech when the input video contains important dialogue or narration.
  • Use ducking when generated music and sound effects should sit behind speech.
  • Keep the input video within 180 seconds and 300 MB.
Note:This website uses AI models provided by third parties.

v1 Video To Video Sound API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/sonilo/v1/video-to-video-sound 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 v1 Video To Video Sound 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",
    "segments": [
        {
            "start": 0,
            "end": 0,
            "prompt": "A cinematic shot of a city at sunset, soft golden light"
        }
    ],
    "preserve_speech": false,
    "ducking": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/sonilo/v1/video-to-video-sound" \
  -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=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 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' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/sonilo/v1/video-to-video-sound";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "segments": [
                {
                        "start": 0,
                        "end": 0,
                        "prompt": "A cinematic shot of a city at sunset, soft golden light"
                }
        ],
        "preserve_speech": false,
        "ducking": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  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",
    "segments": [
        {
            "start": 0,
            "end": 0,
            "prompt": "A cinematic shot of a city at sunset, soft golden light"
        }
    ],
    "preserve_speech": False,
    "ducking": True
}

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/sonilo/v1/video-to-video-sound", 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 = task.get("urls", {}).get("get") or 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"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

v1 Video To Video Sound API — Frequently asked questions

What is the v1 Video To Video Sound API?

v1 Video To Video Sound is a Sonilo model for AI inference, exposed as a REST API on WaveSpeedAI. Sonilo Video to Video Sound adds generated music and sound effects to input videos, creating one or more videos with new audio tracks for video sound design, soundtrack generation, ads, social content, and creative 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 v1 Video To Video Sound 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 production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/sonilo/sonilo-v1-video-to-video-sound.

How much does v1 Video To Video Sound cost per run?

v1 Video To Video Sound starts at $0.018 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 v1 Video To Video Sound accept?

Key inputs: `video`, `ducking`, `music_prompt`, `preserve_speech`, `segments`, `sfx_prompt`. 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/sonilo/sonilo-v1-video-to-video-sound.

How long does v1 Video To Video Sound take to generate?

Median end-to-end generation time on WaveSpeedAI is around 28 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use v1 Video To Video Sound outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Sonilo). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Sonilo Video to Video Sound | WaveSpeedAI