---
title: Sound for video
display: '*Sound* for video'
nav_title: Sound for video
summary:
  - "Make single effects from a description, or let a video to audio model watch the clip and land effects and music on the picture."
  - "Describe physical facts, not reactions, and lock the picture before you generate sound for it."
  - "Scenario makes the tracks; mix dialogue, effects and music in your editor to one loudness target, about -16 LUFS for online video."
description: Generate sound effects from a description or from the clip itself, add music that follows the picture, keep the dialogue already there, and mix a clean track.
section: audio
order: 50
type: guide
level: Build
roles: [creator, artist, art-director, marketer, team-lead, admin, developer]
time: { read: 12, do: 25 }
needs: ["Any plan with credits", "A list of the sounds you need, or a finished cut of the video"]
last_verified: 2026-11-11
models_checked: ["ElevenLabs Sound Effects 2", "Sonilo V1.1 Text to SFX", "MM Audio 2 Text-To-Audio (SFX)", "Sonilo V1.1 Video to SFX", "Sonilo V1.1 - Video to Music", "Sonilo V1.1 Video to Video SFX", "Sonilo V1.1 Video to Video Music", "Kling Video to Audio", "ElevenLabs Voice Isolator", "Audio Extract", "Audio Cut", "Audio Split", "ElevenLabs Sound Effects v3", "Mirelo SFX 2.0 Video to Audio", "Mirelo SFX 2.0 Text to Audio"]
related: [audio-on-scenario, generate-music, game-trailer-cinematic]
pdf: true
thumb: audio/sound-effects-and-foley/thumb.webp
video: tutorials/sound-effects-and-foley.mp4
chapters:
  - { at: 0, title: "A five-second clip with no sound", image: "/media/images/audio/sound-effects-and-foley/ch-01-a-five-second-clip-with-no-sound.webp" }
  - { at: 14.5, title: "Pick an effects model", image: "/media/images/audio/sound-effects-and-foley/ch-02-pick-an-effects-model.webp" }
  - { at: 33.5, title: "Describe the sound", image: "/media/images/audio/sound-effects-and-foley/ch-03-describe-the-sound.webp" }
  - { at: 48.5, title: "Set the length and guidance", image: "/media/images/audio/sound-effects-and-foley/ch-04-set-the-length-and-guidance.webp" }
  - { at: 57, title: "The effect: creak, then thud", image: "/media/images/audio/sound-effects-and-foley/ch-05-the-effect-creak-then-thud.webp" }
  - { at: 81.5, title: "Start from the video", image: "/media/images/audio/sound-effects-and-foley/ch-06-start-from-the-video.webp" }
  - { at: 109, title: "A clip with dialogue", image: "/media/images/audio/sound-effects-and-foley/ch-07-a-clip-with-dialogue.webp" }
  - { at: 120.5, title: "Scenario makes the tracks, you mix them", image: "/media/images/audio/sound-effects-and-foley/ch-08-scenario-makes-the-tracks-you-mix-them.webp" }
  - { at: 144, title: "Recap", image: "/media/images/audio/sound-effects-and-foley/ch-09-recap.webp" }
steps:
  - title: "Pick an effects model"
    text: "Create › Audio › the model name › View all models, tick Audio under Output and Sound Effects under Capabilities. ElevenLabs Sound Effects v3 gives a set length and a loop switch; Sonilo V1.1 Text to SFX gives many variations in lossless formats."
  - title: "Describe the sound"
    text: "In Sound Description, in this order: the source and material, the action in stages, the space, and what to leave out. Describe the sound, not the reaction."
    prompt: |-
      A heavy wooden door with iron hinges creaks open slowly, then closes with a solid thud, inside a stone hallway with a short echo. No music, no voices.
  - title: "Set the length and guidance, then generate"
    text: "Duration 5 seconds with room for the tail, Guidance raised from 0.3 to 0.5, Loop off for a one-shot, Output Format MP3, then Generate. For rain or a room tone, describe a steady sound and turn Loop on; make each layer on its own."
  - title: "Start from the video"
    text: "Lock the cut, pick Sonilo V1.1 Video to SFX and add the clip under Video. Leave Prompt empty or name the key sounds in one line, use Add Segments for distinct scenes, set Settings › Audio Format to WAV and Generate."
    prompt: |-
      Footsteps on paving stones, a busy market crowd, fabric flapping in a light breeze
  - title: "Music, and dialogue that's already there"
    text: "Sonilo V1.1 - Video to Music makes music that follows the clip, as its own track. To protect existing dialogue, pull the audio out with Audio Extract, keep only the voice with ElevenLabs Voice Isolator, then add the new sound around it."
  - title: "Mix the tracks"
    text: "In your editor: dialogue first, effects on their events, music under the voice, and one loudness target of about -16 LUFS integrated for online video. Audio Cut, Audio Split and Audio Extract handle quick fixes in Scenario."
agent_steps:
  - title: "Connect the Scenario MCP"
    text: "Connect your agent and sign in once at [mcp.scenario.com](https://mcp.scenario.com). Then tell it which Scenario team and project to use, so every file lands there."
  - title: "Give the agent the clip"
    text: "The locked cut of the clip that needs sound: upload it with upload_asset or give its asset ID. Don't trim it afterwards, or the sound no longer lines up."
  - title: "Brief the agent: a single effect"
    prompt: |-
      Make the door effect with ElevenLabs Sound Effects 2 (model_elevenlabs-sound-effects-v2), reading model_schema_get first for the parameter names: duration 5 seconds, guidance 0.5, loop off. Make two takes. Sound description, word for word:
      A heavy wooden door with iron hinges creaks open slowly, then closes with a solid thud, inside a stone hallway with a short echo. No music, no voices.

      Quote the cost with a dry run first and wait for my go.
  - title: "Brief the agent: sound for the clip"
    prompt: |-
      Run Sonilo V1.1 Video to SFX (model_sonilo-v1-1-video-to-sound-effects) on my clip, reading model_schema_get first. Audio format WAV. Prompt, word for word:
      Footsteps on paving stones, a busy market crowd, fabric flapping in a light breeze

      Quote the cost with a dry run first and wait for my go.
  - title: "Check and redo"
    text: "Accept when every stage you described is audible in order, impacts and footsteps land on their frames, tails fade naturally and no voice or melody appears. Reject a missing stage, music under an effect or a sound early or late by more than a couple of frames; then raise guidance or name the sound more precisely."
    prompt: |-
      Wait for the jobs with jobs_wait and show me each take with asset_display. Report each take's length, and redo only the ones I reject.
  - title: "File, download and report"
    prompt: |-
      Create a collection for the clip's sound with the approved takes, download each one with asset_download for my editor, and report the models, the settings and every asset ID.
updated: 2026-11-11
canonical: https://learn.scenario.com/audio/sound-effects-and-foley
---

Last updated: 2026-11-11

# Sound for video

> Generate sound effects from a description or from the clip itself, add music that follows the picture, keep the dialogue already there, and mix a clean track.

In short:

- Make single effects from a description, or let a video to audio model watch the clip and land effects and music on the picture.
- Describe physical facts, not reactions, and lock the picture before you generate sound for it.
- Scenario makes the tracks; mix dialogue, effects and music in your editor to one loudness target, about -16 LUFS for online video.


This lesson gives a silent clip its sound. You'll make a single effect from a description with ElevenLabs Sound Effects v3, let Sonilo V1.1 Video to SFX watch a locked clip and generate effects timed to it, and then see how the tracks come together in one mix.

:::note As of November 2026
The models, settings and screens in this article are the ones Scenario offered in November 2026. New models and updates arrive often, so check the app for newer options before you choose.
:::

:::steps Quick version
1. For one sound, open **Create** › **Audio** and pick a model under **Sound Effects**, such as **ElevenLabs Sound Effects v3**.
2. In **Sound Description**, name the source and material, the action in stages, the space, and what to leave out.
3. Set **Duration** with room for the tail, raise **Guidance** if a take ignores part of the description, turn on **Loop** for a steady sound.
4. For sound that follows the picture, lock the cut, pick **Sonilo V1.1 Video to SFX**, add the clip, set **Audio Format** to **WAV**, and generate.
5. Mix the tracks in your editor: dialogue first, effects on their events, music under the voice, one loudness target.
:::

## Before you start

- **Know which kind of sound you need.** A single effect (a door, footsteps, wind) comes from a description. Sound that has to follow a moving picture comes from the video itself.
- **Lock the picture first** if you start from a clip. Every trim after generation moves the picture away from the sound.
- **Scenario makes the tracks; you mix them** in your audio or video editor.
- **Takes are cheap compared with video.** Make two or three of anything you'll use. The cost shows on the **Generate** button.

![Sound for a video as three tracks under a locked picture: dialogue on top, effects on their events, music under the voice, then one mix at about -16 LUFS for online video](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/51fc1c95c1bc0ff85ea2540701380368610dcf3639f12ced61e2509d32db4527.svg "Three tracks under a locked picture, then one mix.")

### Models

| You need | Model | Notes |
|---|---|---|
| A precise single effect with a set length, or a loop | ElevenLabs Sound Effects v3, ElevenLabs Sound Effects 2 | **Duration**, **Guidance**, **Loop**; Sound Effects 2 makes 0.5 to 30 seconds |
| Many variations, in lossless formats | Sonilo V1.1 Text to SFX, MM Audio 2 Text-To-Audio (SFX) | WAV or FLAC output; Sonilo makes 1 to 180 seconds |
| Effects for a clip, as a separate track | Sonilo V1.1 Video to SFX | Optional prompt, timed segments |
| Music that follows a clip, as a separate track | Sonilo V1.1 - Video to Music | Reads the clip's pacing, motion and mood |
| The clip back with effects or music mixed in | Sonilo V1.1 Video to Video SFX, Sonilo V1.1 Video to Video Music | A finished clip, for one that goes out as is |
| Effects and music on a short clip | Kling Video to Audio | Clips of 3 to 20 seconds |

Take a separate track when you'll mix, add narration or adjust levels; take the video with sound in it for a single clip that goes out as is. A music cue with an exact length comes from a music model ([Generate music](https://learn.scenario.com/audio/generate-music.md)).

## Step 1: Pick an effects model

Open **Create** › **Audio**, click the model name, then **View all models**. Tick **Audio** under **Output** and **Sound Effects** under **Capabilities**.

![Choose a model filtered to Sound Effects: ElevenLabs Sound Effects v3, Mirelo SFX 2.0, Sonilo V1.1 Text to SFX and Video to SFX, MM Audio 2 and ElevenLabs Sound Effects 2](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/a9fd1ad72b7e1a7197ff1532b381a0630324f71ddfeeba6377d98d10077aacb6.webp)

- **ElevenLabs Sound Effects** gives you a set length and a loop switch. This lesson uses **v3**.
- **Sonilo V1.1 Text to SFX** gives many variations, in lossless formats.

## Step 2: Describe the sound

The main field is called **Sound Description**. An effects model reads physical facts, so give it, in this order:

1. **The source and material:** "A heavy wooden door with iron hinges."
2. **The action, in stages:** "creaks open slowly, then closes with a solid thud."
3. **The space:** "inside a stone hallway with a short echo." The space changes the sound as much as the source.
4. **What to leave out:** "No music, no voices." Effect models can add both.

```prompt
A heavy wooden door with iron hinges creaks open slowly, then closes with a solid thud, inside a stone hallway with a short echo. No music, no voices.
```

**Describe the sound, not the reaction.** "Massive", "cinematic" or "scary" won't help. Write what makes it scary instead: "a slow low creak, then silence".

## Step 3: Set the length and guidance, then generate

Below the description:

- **Duration:** set the length with a little room after the last sound, so the tail can fade. Here **5** seconds.
- **Guidance:** how closely the take follows the description. It opens at 0.3; here it's raised to **0.5**. If a take ignores part of your description, raise it. Lower it to let the model vary the sound.
- **Loop:** leave it off for a one-shot like this door.
- **Output Format:** MP3 by default.

Click **Generate**. The take arrives at 00:05, with the creak, then the thud, in a stone hallway.

![ElevenLabs Sound Effects v3 with the door description, Duration 5, Guidance 0.5, Loop off, and the 00:05 take](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/51b883de914d791eb0156a2b7fb8effaa0e7fad873b0967f3bba9dd811f3a216.webp)

Here is the same description on ElevenLabs Sound Effects 2, at 5 seconds:

<audio controls src="https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/2a7a2c79966b9d35a781291adef911595a53e2e8aabbfebf79410de39fba63f4.mp3"></audio>

### Loops

For rain, a room tone or an engine, describe a steady sound with no beginning or end event, such as "steady light rain on a tin roof, constant, no thunder", and turn **Loop** on. Play the take twice back to back and listen for a click at the join.

### Layers

Real effects are often layers: a **body** (the heavy door closing), a **detail** (the iron latch clicking) and a **space** (the stone room's tail). Make each one on its own, so you can balance them later and redo a bad layer cheaply.

## Step 4: Start from the video

When the sound has to follow the picture, start from the clip. **Lock the cut first**: every trim afterwards moves the picture away from the sound, and you'd have to generate again.

1. Pick **Sonilo V1.1 Video to SFX** in the model menu.
2. Under **Video**, add the clip.
3. Leave **Prompt** empty to let the model describe the clip, or name the key sounds in one line:

```prompt
Footsteps on paving stones, a busy market crowd, fabric flapping in a light breeze
```

4. For a clip with distinct scenes, click **Add Segments** and give each part its own description.
5. Under **Settings**, set **Audio Format** to **WAV** if you'll mix it.
6. Click **Generate**.

![Sonilo V1.1 Video to SFX with the market clip, a one-line Prompt, Segments with Add Segments, and Audio Format WAV](https://ufgc0c9mhl4ueq76.public.blob.vercel-storage.com/academy/d888d93a7b19bf77c8c94c75718b716f1eff734936f2c2d58cfbe54999a91dd8.webp)

Then play the clip with its new track and check the hardest moments: impacts, footsteps, doors. They should land on the frames where they happen.

## Step 5: Music, and dialogue that's already there

- **For music that follows the clip,** use **Sonilo V1.1 - Video to Music** the same way. It reads the clip's pacing and mood and returns the music as its own track.
- **If the clip already has dialogue, protect it.** Pull the audio out with **Audio Extract**, keep only the voice with **ElevenLabs Voice Isolator**, then add the new sound around it. The Video to Video models can also keep existing speech.

## Step 6: Mix the tracks

Scenario makes the tracks; you mix them in your editor, in this order:

1. **Dialogue or narration first,** at a steady level.
2. **Effects on their events.** Nudge a few frames if an impact lands early or late.
3. **Music under the voice,** lower while someone speaks.
4. **One loudness target for the whole piece:** about -16 LUFS integrated for online video, checked with a loudness meter.

For quick fixes without an editor, three tools run in Scenario. Find them by name in the model menu:

| Tool | What it does |
|---|---|
| **Audio Cut** | Trims a track to a time range |
| **Audio Split** | Divides a track at the times you give |
| **Audio Extract** | Pulls the sound out of a video |

For a series, keep a sound list (time range, sound, prompt, kept asset) and run it through one node in a [workflow](https://learn.scenario.com/workflows/what-are-workflows.md). The [trailer playbook](https://learn.scenario.com/playbooks/game-trailer-cinematic.md) runs the whole process on one piece.

:::check
**Accept when:** every stage you described is audible in order, impacts and footsteps land on their frames, the sounds match the materials on screen, tails fade naturally and loops repeat without a click, existing dialogue stays clear, music sits under the voice, and the loudness is even from start to end.
**Reject when:** a stage is missing or out of order, a voice or melody appears that you didn't ask for, a sound arrives early or late by more than a couple of frames or has nothing on screen to cause it, original speech is muffled, or the level jumps between shots.
:::

## Common problems

| What you see | What to do |
|---|---|
| The sound is generic or wrong | Name the material and the space; for a clip, name the key sounds and use segments where the scene changes |
| A take ignores part of the description | Raise **Guidance**, or split the sound into layers |
| A specific sound comes out as something else | Describe its shape: rising or falling pitch, how fast, how loud |
| Music or voices appear in an effect | Add "No music, no voices" and remove words that suggest a scene with people |
| The tail is cut off | Raise **Duration** so there's room after the last sound |
| A loop clicks at the join | Describe a steady sound with no start or end event, with **Loop** on |
| Sound out of sync with the clip | Check the clip wasn't trimmed after generation; generate again on the final cut, or nudge the track |
| Dialogue damaged, or music covers it | Use the layered route (**Audio Extract**, Voice Isolator, new sound), or lower the music under each line |
| The job failed or is stuck | See [Failed or stuck jobs](https://learn.scenario.com/browse#help-center) |

## What's next

Next, [Transcribe and subtitle](https://learn.scenario.com/audio/transcribe-and-subtitle.md) turns speech into a transcript, an SRT you can fix, and subtitles burned into the video. To make the score for a clip, see [Generate music](https://learn.scenario.com/audio/generate-music.md).

Source: https://learn.scenario.com/audio/sound-effects-and-foley