API reference · Sonilo

sonilo/1.1/video-to-video-music

Integrate this model through SandBase's unified API, with production-ready schemas and examples.

VIDEOAsyncOpen model

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDsonilo/1.1/video-to-video-music

Input Schema

7 parameters · 1 required · 6 optional

Parameter	Type	Required	Description
`prompt`	string	Required	Optional text prompt steering the musical style. If omitted, a prompt is generated automatically from the video.
`video`	string	Optional	Public http(s) URL of the source video to score.
`duration`	integer	Optional	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 (None) to the rest of the video. · Min: 1 · Max: 600
`num_samples`	integer	Optional	How many distinct scored videos to generate. · Min: 1 · Max: 3 · Default: 1
`start_offset`	number	Optional	Optional. Start scoring from this offset (seconds) into the video. Requires Start Offset + Duration <= Video Duration. · Min: 0 · Max: 600
`prompt_influence`	number	Optional	Turn it up to match the text prompt · Min: 0 · Max: 1 · Default: 0.5
`keep_speech_vocal`	boolean	Optional	Keep the original video's speech/vocals. When on, the source audio is separated (music source separation), and only the isolated vocals are blended over the generated music with automatic ducking (the music dips under speech). When off (default), the original soundtrack is dropped and the video carries only the generated music. · Default: false

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "sonilo/1.1/video-to-video-music",
  "video": "https://v3b.fal.media/files/b/0a9ddd00/2QssaYyFxstvVlmIraSns_Sonilo_Demo_Original_1.mp4",
  "num_samples": 1,
  "prompt_influence": 0.5,
  "keep_speech_vocal": false,
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to V1.1 Video to Video Music