Sound for video

Connect the Scenario MCP

Connect your agent and sign in once at mcp.scenario.com. Then tell it which Scenario team and project to use, so every file lands there.

Give the agent the clip

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.

Brief the agent: a single effect

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.

Brief the agent: sound for the clip

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.

Check and redo

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.

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.

File, download and report

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.

Pick an effects model

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.

Describe the sound

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.

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.

Set the length and guidance, then generate

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.

Start from the video

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.

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

Music, and dialogue that's already there

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.

Mix the tracks

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.