mirelo/video-to-sfx-v1.5 🔢🖼️📝 → 🖼️

⭐ Official ▶️ 2.8K runs 📅 Oct 2025 ⚙️ Cog 0.16.9

About

Generate synced sounds for any video and return it with its new soundtrack - now enhanced in version 1.5 for improved sound synchronization and realism

Example Output

Output

Performance Metrics

23.27s Prediction Time

23.29s Total Time

All Input Parameters

{
  "steps": 25,
  "duration": 10,
  "video_path": "https://replicate.delivery/pbxt/NjAV16ybJgqVddjbI73DMEqSyOI9G7ONpSaTqbENgg0aHKrL/video_1.mp4",
  "num_samples": 2,
  "text_prompt": "",
  "start_offset": 0,
  "creativity_coef": 4.5
}

Input Parameters

seed Type: integer: Random seed for reproducibility. Leave blank (None) or use -1 for random seed, or any integer for deterministic results.
steps Type: integerDefault: 25Range: 1 - 30: Number of processing steps for the generation model. Higher values may improve quality but take longer.
duration Type: integerDefault: 10Range: 1 - 10: Duration of the generated sound effects in seconds.
video_path (required) Type: string: Video file to process for sound effects. Video will be trimmed to 10 sec if longer
num_samples Type: integerDefault: 2Range: 1 - 4: Number of sound effects to generate. Each sample will be a different variation.
text_prompt Type: stringDefault:: Text prompt to guide sound effect generation. Optional text to guide the sound generation process.
start_offset Type: numberDefault: 0Range: 0 - 300: Starting point in the video (in seconds) from which to generate audio. 0 means start from the beginning.
creativity_coef Type: numberDefault: 4.5Range: 1 - 10: Creativity coefficient to control the creativity of the generated sound. Higher values are more creative.

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Using seed: 304957528
Uploading video to S3...
Video uploaded successfully
Using seed: 304957528
Generating 2 sound effects (no text prompt provided)
Generated 2 sound effects in 18.5sec
Downloading output 1/2...
Downloading 8947025 bytes
Downloaded 8.53MB in 1.46sec
Downloading output 2/2...
Downloading 8946931 bytes
Downloaded 8.53MB in 0.66sec
Unit calculation:
  Duration: 10 seconds
  Samples: 2
  Total units: 10 × 2 = 20
---------------------------

Version Details

Version ID: aed445442662392d9dd89a0129557166902c20bf31ba90dcb1b68edf4cea24a7
Version Created: November 14, 2025

Run on Replicate →