Skip to content
Get started
GENERATION API CALLS
Audio Generation

Sonilo

This page is auto-generated from model configurations. Last updated: 2026-08-17.

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


Turn a text description into original music — specify the style, mood, and instrumentation, and get back a ready-to-use audio track in seconds.

Model ID: model_sonilo-v1-1-text-to-music

Capabilities: txt2audio

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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
promptstringYes----Describe the music you want — genre, mood, instruments, tempo, and structure. For example: ‘upbeat lo-fi hip hop with soft piano and vinyl crackle’ or ‘epic orchestral build for a battle scene’.
durationnumberNo901600-How long the generated track should be, in seconds. Longer tracks cost more.
numSamplesnumberNo113-How many variations to generate from the same prompt. Useful for picking the best take. Each additional sample adds to the cost.

Generate high-quality, commercial-use-safe sound effects from a text prompt with control over texture, intensity, and exact duration

Model ID: model_sonilo-v1-1-text-to-sound-effects

Capabilities: txt2audio

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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
promptstringYes----Describe the sound you want to create — for example: ‘Deep rolling thunder rumbling across the sky with heavy rain pouring on the ground’.
durationnumberNo81180-How long the audio should be, in seconds. Longer clips cost more.
audioFormatstringNoaac--aac, mp3, wav, flacFormat of the returned audio file.

Upload a video and get back an original soundtrack that matches its pacing, mood, and timing

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

Capabilities: video2audio

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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
videofileYes----The video to generate a soundtrack for. The model analyzes its pacing, mood, and visual rhythm to produce music that fits. Cost scales with video duration.
promptstringNo----Optional style guidance for the generated music. If omitted, Sonilo generates a prompt from the video.
numSamplesnumberNo113-How many soundtrack variations to generate from the same video. 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.

Analyze a video and generate synchronized, royalty-free sound effects timed to visible actions — returns the audio track for commercial use

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

Capabilities: video2audio

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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
videofileYes----The video to generate sound effects for. The generated audio matches the video length. Cost scales with video duration.
promptstringNo----Optional. Describe the kind of sound you want; it steers the generated audio for every scene. Leave empty to caption the video automatically.
segmentsinputs_arrayNo----Optional. Split the video into contiguous time ranges, each with its own sound description. The first segment must start at 0; leave empty to split into scenes automatically.
audioFormatstringNoaac--aac, mp3, wav, flacFormat of the returned audio file.