Sonilo V1.1 · Video to Sound Effects

ABOUT THE WORKFLOW

Add Sound Effects to a Video
Upload a video and get it back with synced sound effects. The model watches the footage, matches sounds to visible actions, and returns a finished audio track mixed into the clip. Optionally use time-based segments to control what plays at specific moments.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

• Sonilo V1.1 Sound Effects by Sonilo. A video-native sound model that analyzes on-screen motion and scene context, then generates synchronized foley and ambience. All generated audio is royalty-free and cleared for commercial use.

HOW IT WORKS

Step 1. Upload your video
The footage you want sound effects added to. Upload your own or replace the default.
Works great with: AI-generated clips · silent footage · renders · short films

Step 2. Review the sound prompt
A cinematic foley instruction is pre-filled and works for most clips. Rewrite it to match your footage, or leave the default for general-purpose sound design.

Step 3. Set segments (optional)
Five time-based slots let you control what sounds play at specific moments. Set an end time and a sound prompt for each segment. Gaps between segments fall back to the main prompt.

Step 4. Hit run and download
The model watches your footage, generates synced sound effects, and returns the video with audio mixed in. Preview it in the workflow, then download.
Ready for: Premiere · DaVinci Resolve · After Effects · any NLE

First time? Leave every setting as-is. The defaults (mp3 · pre-filled prompt · no segments) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard sound design (most people) — mp3 · pre-filled prompt · no segments. The right starting point for almost everyone.

• Want sounds tailored to your footage — Rewrite the main prompt to name the specific sounds in your clip. "Footsteps on gravel, wind through trees, distant traffic" is more useful than the generic default.

• Clip has distinct scenes — Use segments. Set an end time for each scene and write a separate sound prompt for it. The model switches sound direction at each boundary.

• The sounds do not match the action — Be more specific in the prompt about what is visible. Name the surfaces, materials, and environment. "Boots on wet concrete" lands better than "footsteps."

• Want ambience without action sounds — Rewrite the prompt to focus on environment only. "Quiet forest ambience, light breeze, distant birdsong, no footsteps" narrows what the model generates.

• Need a different audio format — Switch the audio format setting from mp3 to match your post-production pipeline.

Prompt: Describe the sounds you want to hear, not the visuals you see. "Footsteps on wood floor, door creak, rain on glass, muffled city traffic outside" gives the model clear targets. Avoid asking for dialogue, narration, vocals, or music. The model generates sound effects only.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

🎬 AI Video Post-Production
Add foley to silent AI-generated clips from models like Wan, Kling, or MiniMax H3. Upload the clip and get it back with footsteps, impacts, and ambience synced to the action.

🎞️ Trailer and Showreel Polish
Layer in cinematic sound design without opening a DAW. The model reads the footage and generates a full effects track in one pass.

🛍️ Product and Ad Videos
Add realistic handling sounds, environment ambience, or subtle movement to product shots and commercial footage.

🎮 Game and Motion Design
Generate synced foley for animation, game trailers, or motion graphics where building a sound library from scratch would take longer than the edit itself.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Silent AI-generated video clips

• Footage with clear, visible actions (walking, impacts, doors, vehicles)

• Prompts that name specific sounds and surfaces

• Segments for clips with distinct scene changes

⚠️ May produce softer results

• Footage with existing audio (the model adds on top, does not replace)

• Expecting dialogue, narration, vocals, or music

• Vague prompts like "add good sounds"

• Very long clips with no visible action

FAQ

What is Sonilo Sound Effects V1.1?
Sonilo Sound Effects V1.1 is a video-native AI sound model by Sonilo, launched on fal.ai in July 2026 with a V1.1 update following shortly after. It watches video footage, analyzes on-screen motion and scene context, and generates a synchronized sound effects track. It produces foley and ambience only, not dialogue or music.

How does Sonilo match sounds to video?
The model analyzes the footage for on-screen actions, timing, environments, and transitions before generating audio. Footsteps sync to walking, impacts sync to collisions, ambience matches the visible environment. An optional text prompt lets you steer which sounds the model prioritizes or what creative direction to take.

What are segments and when should I use them?
Segments are five time-based slots that let you give the model a different sound prompt for different parts of the video. Set an end time and a sound description for each. Use them when a clip has distinct scenes, like an indoor shot followed by an outdoor shot, where one global prompt would not cover both. Gaps between segments fall back to the main prompt.

Can Sonilo generate dialogue, vocals, or music?
No. This model generates sound effects only. Footsteps, impacts, movement, ambience, and environmental sounds. For music, Sonilo offers a separate video-to-music model.

Are the generated sound effects royalty-free?
Yes. All audio generated by Sonilo is royalty-free and cleared for commercial use. You can use the output in shipped projects, client work, and broadcast without additional licensing.

Does this replace the existing audio on my video?
No. The model generates a new sound effects track and mixes it into the video. If your clip already has audio, the generated effects layer on top. For clean results, start with silent or near-silent footage.

How to run Sonilo Sound Effects online?
You can run Sonilo Sound Effects online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload a video, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A sound designer runs a clip and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it?
Upload a video and run it. The sound prompt is already set.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.