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.
Bezczynny
$0.01za uruchomienie·~100 / $1
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.
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.
| Parameter | Required | Description |
|---|---|---|
| video | Yes | Video URL or uploaded video to add synchronized sound effects to. |
| prompt | No | Optional text prompt to guide the generated sound effects. |
| duration | No | Duration of the generated SFX audio in seconds. Range: 1–60. Default: 10. This does not extend the input video. |
| num_samples | No | Number of variations to generate. Range: 1–4. Default: 1. |
| seed | No | Seed for reproducibility. Use -1 for a random seed. Default: -1. |
1 to 4.-1 for random output, or a fixed value for more reproducible results.Cinematic trailer sound design with deep impacts, airy risers, subtle whooshes, and tense low-end atmosphere
Pricing is based on generated SFX duration and number of samples.
| Duration | 1 Sample | 2 Samples | 3 Samples | 4 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 |
duration and num_samplesprompt and seed do not affect pricingduration does not extend the input videonum_samples when you want multiple design options from the same clip.seed when comparing prompt changes on the same source video.video is required.duration supports 1–60 seconds.num_samples supports 1–4.seed = -1 means random generation.duration refers to the SFX audio length only and does not extend the uploaded video.