Vidu Q3 與 Q3 Pro 模型 5 折 · 僅限 WaveSpeedAI | 5月20日 – 6月2日

Mirelo SFX1.6 Video to Audio API

mirelo-ai /

Mirelo SFX1.6 Video to Audio is a fast AI audio generation model that creates synchronized sound effects for video and returns the video with a new audio track. Supports clips up to 60 seconds. Ready-to-use REST inference API for video sound design, synced SFX generation, game trailers, social media clips, cinematic videos, product demos, and professional audio-for-video workflows with simple integration, no coldstarts, and affordable pricing.

video-dubbing
輸入

拖放檔案或點擊上傳

就緒

$0.01每次運行·~100 / $1

示例查看全部

相關模型

README

Mirelo AI SFX 1.6 Video-to-Video

Mirelo AI SFX 1.6 Video-to-Video generates synchronized sound effects for an uploaded video, with optional prompt guidance, multiple variations, and seed control for reproducibility. It is designed for adding or redesigning audio for short videos, trailers, demos, gameplay clips, and other visual content workflows.

Why Choose This?

  • Video-to-sound workflow Generate synchronized sound effects directly from video input.

  • Prompt-guided audio generation Add an optional text prompt to steer the type, mood, or intensity of the generated sound effects.

  • Multiple variations Generate up to 4 variations in one request with num_samples.

  • Flexible audio duration Choose how many seconds of SFX audio to generate, up to 60 seconds.

  • Seed support Use seed for more reproducible results, or -1 for random generation.

  • Production-ready API Useful for sound design, trailer audio, short-form video, social content, and creative audio workflows.

Parameters

ParameterRequiredDescription
videoYesVideo URL or uploaded video to add synchronized sound effects to.
promptNoOptional text prompt to guide the generated sound effects.
durationNoDuration of the generated SFX audio in seconds. Range: 1–60. Default: 10. This does not extend the input video.
num_samplesNoNumber of variations to generate. Range: 1–4. Default: 1.
seedNoSeed for reproducibility. Use -1 for a random seed. Default: -1.

How to Use

  1. Upload your video — provide the source video you want to add sound effects to.
  2. Add a prompt (optional) — describe the sound design, mood, or effect direction you want.
  3. Set duration — choose how many seconds of synchronized SFX audio to generate.
  4. Set number of samples — choose how many variations you want, from 1 to 4.
  5. Set a seed (optional) — use -1 for random output, or a fixed value for more reproducible results.
  6. Submit — run the model and download the generated audio outputs.

Example Prompt

Cinematic trailer sound design with deep impacts, airy risers, subtle whooshes, and tense low-end atmosphere

Pricing

Pricing is based on generated SFX duration and number of samples.

Duration1 Sample2 Samples3 Samples4 Samples
1s$0.01$0.02$0.03$0.04
5s$0.05$0.10$0.15$0.20
10s$0.10$0.20$0.30$0.40
20s$0.20$0.40$0.60$0.80
30s$0.30$0.60$0.90$1.20
60s$0.60$1.20$1.80$2.40

Billing Rules

  • Pricing is $0.01 per generated second
  • Pricing increases with both selected duration and num_samples
  • prompt and seed do not affect pricing
  • Billing is based on the generated SFX audio duration, not the source video duration
  • The selected duration does not extend the input video

Best Use Cases

  • Trailer and teaser sound design — Add cinematic effects to short video clips.
  • Social content enhancement — Generate sound layers for reels, shorts, and promotional videos.
  • Game and app previews — Add designed effects to gameplay or demo footage.
  • Prototype audio direction — Quickly explore multiple sound directions from the same video.
  • Creative post-production — Generate synced SFX for short-form editing workflows.

Pro Tips

  • Use a prompt only when you want stronger control over the sound style or mood.
  • Increase num_samples when you want multiple design options from the same clip.
  • Start with shorter durations for testing, then extend if the direction feels right.
  • Use a fixed seed when comparing prompt changes on the same source video.
  • Clear visual motion in the video usually helps produce more meaningful synchronized sound effects.

Notes

  • video is required.
  • duration supports 1–60 seconds.
  • num_samples supports 1–4.
  • seed = -1 means random generation.
  • The generated duration refers to the SFX audio length only and does not extend the uploaded video.
  • Pricing depends on generated duration and sample count.

Related Models

  • Mirelo AI SFX 1.6 Text-to-Audio — Generate sound effects or ambient audio directly from text prompts.
  • Mirelo AI SFX 1.6 Extend Audio — Extend an existing audio clip with newly generated continuation.
  • Mirelo AI SFX 1.6 Inpaint Audio — Regenerate a selected segment inside an existing audio clip.
無障礙:本網站使用的 AI 模型由第三方提供。