Skip to content
Get started
GENERATION API CALLS
Video Generation

Sonilo

This page is auto-generated from model configurations. Last updated: 2026-07-29.

This reference lists all available Sonilo video generation models and their parameters. Use these parameter names when calling the Generation API.


Generate a perfectly synced, commercially licensed soundtrack for any video β€” optionally keeping the original speech while replacing the music

Model ID: model_sonilo-v1-1-video-to-video

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_sonilo-v1-1-video-to-video/markdown

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
videofileYes----The video to score with a new soundtrack. The model analyzes its pacing, mood, and visual rhythm to produce music that fits, then muxes it back into the video. Cost scales with video duration.
promptstringNo----Optional style guidance for the generated music. If omitted, Sonilo generates a prompt from the video.
keepSpeechVocalbooleanNofalse---When enabled, the original speech/vocals are isolated and blended over the generated music with automatic ducking. When off (default), the original soundtrack is replaced entirely.
numSamplesnumberNo113-How many scored video variations to generate from the same source. Useful for picking the best fit. Each additional sample adds to the cost.
startOffsetnumberNo-0600-Optional. Start scoring from this offset in the video, in seconds. Start offset plus duration must not exceed the video duration.
durationnumberNo-1600-Optional. Length (seconds) of the video segment to score. When set, scores a segment of this length starting at Start Offset (or from the beginning if Start Offset is unset). Defaults to the rest of the video: the whole video when Start Offset is unset, or from Start Offset to the end when it is set.