Sonilo GenerateMusicFromText
CertifiedGenerate music from a text prompt
Sonilo GenerateMusicFromText
Generate music from a text prompt
Sends the prompt to POST /v1/text-to-music and stores the audio in Kestra internal storage. Stream mode is the default. wav, mp3, multiple variants, and stems switch the request to async and poll GET /v1/tasks/{task_id}. Killing the task stops the local wait only. Sonilo has no cancel endpoint, so remote work can continue and can still be billed.
type: io.kestra.plugin.sonilo.GenerateMusicFromTextExamples
Generate a short music bed from a prompt
id: generate_music_from_text
namespace: company.media
tasks:
- id: generate_music
type: io.kestra.plugin.sonilo.GenerateMusicFromText
apiToken: "{{ secret('SONILO_API_TOKEN') }}"
prompt: "Warm analog synths under a quiet piano"
duration: 30
Properties
apiToken *string
Sonilo API token
Bearer token from a Sonilo Platform account at platform.sonilo.com. Platform keys are separate from sonilo.com app logins. Sent as Authorization: Bearer.
prompt *string
Music prompt
Describes the music to generate. Sonilo documents a practical limit of 2000 characters.
assets
Assets this task consumes as inputs or produces as outputs, for lineage tracking and the asset graph (Enterprise Edition). A flow declaring this property on a task is rejected in the open-source edition.
io.kestra.core.models.assets.AssetsDeclaration
IGNOREFAILWARNAsset failure behavior
Behavior applied to the task state when a declared asset fails to render, emit, or be persisted (e.g. a lock conflict): FAIL escalates it to FAILED, WARN (default) warns it if it would otherwise succeed, IGNORE leaves the state untouched.
Whether to auto-register assets referenced dynamically at runtime that are not statically declared in inputs or outputs.
The assets consumed as inputs.
io.kestra.core.models.assets.AssetIdentifier
1The assets produced as outputs.
io.kestra.plugin.ee.assets.Dataset
1150{}1150io.kestra.plugin.ee.assets.File
1150{}1150io.kestra.plugin.ee.assets.Table
1150{}1150io.kestra.plugin.ee.assets.VM
1150{}1150io.kestra.core.models.assets.External
1150{}1150io.kestra.core.models.assets.Custom
11501Custom asset type
{}1150baseUrl string
https://api.sonilo.comSonilo API base URL
API host root. Defaults to https://api.sonilo.com. A trailing slash, or a base that already ends in /v1, is accepted.
duration integerstring
Duration in seconds
Optional integer from 5 to 360. When omitted, Sonilo chooses the length.
mode string
streamasyncGeneration mode
stream returns NDJSON audio. async returns a task id and is required for wav, mp3, multiple variants, and stems. When omitted, the task selects async if one of those options is set.
options
HTTP client configuration
Optional proxy, timeout, and TLS settings for calls to the Sonilo API.
io.kestra.core.http.client.configurations.HttpConfiguration
falseIf true, allow a failed response code (response code >= 400)
List of response code allowed for this request
The authentication to use.
io.kestra.core.http.client.configurations.BasicAuthConfiguration
The password for HTTP basic authentication.
The username for HTTP basic authentication.
io.kestra.core.http.client.configurations.BearerAuthConfiguration
The token for bearer token authentication.
io.kestra.core.http.client.configurations.DigestAuthConfiguration
The password for HTTP Digest authentication.
The username for HTTP Digest authentication.
UTF-8The default charset for the request.
java.nio.charset.Charset
trueWhether to enable TCP Keep-Alive extended socket options (TCP_KEEPIDLE, TCP_KEEPINTERVAL, TCP_KEEPCOUNT).
Set to false when running on Windows workers, as these extended socket options are not supported by the Windows JDK and will cause connection failures.
trueWhether redirects should be followed automatically.
REQUEST_HEADERSREQUEST_BODYRESPONSE_HEADERSRESPONSE_BODYThe enabled log.
The proxy configuration.
io.kestra.core.http.client.configurations.ProxyConfiguration
The address of the proxy server.
The password for proxy authentication.
The port of the proxy server.
DIRECTDIRECTHTTPSOCKSThe type of proxy to use.
The username for proxy authentication.
The SSL request options
io.kestra.core.http.client.configurations.SslOptions
Whether to disable checking of the remote SSL certificate.
Only applies if no trust store is configured. Note: This makes the SSL connection insecure and should only be used for testing. If you are using a self-signed certificate, set up a trust store instead.
The timeout configuration.
io.kestra.core.http.client.configurations.TimeoutConfiguration
The time allowed to establish a connection to the server before failing.
PT5MThe time allowed for a read connection to remain idle before closing it.
outputFormat string
m4awavmp3Output format
m4a, wav, or mp3. wav and mp3 require async mode. Streaming audio is always m4a.
pollInterval string
PT3STime between Sonilo task status checks
Used after an async submission while waiting for GET /v1/tasks/{task_id}. Defaults to PT3S.
segments string
Segment plan
Optional JSON string of timed segment prompts. Sent as the segments form field.
stems booleanstring
Also return separated stems
When true, Sonilo adds drums, bass, vocals, and other stems. Requires async mode. Stem failure does not fail the generation.
variantsNum integerstring
Number of variants
Optional integer from 1 to 10. Values above 1 require async mode and are billed per variant.
waitTimeout string
PT30MMaximum time to wait for a Sonilo task
Async generation, including stem separation, is polled until this timeout. Defaults to PT30M. Stem separation often finishes in a few minutes and can run much longer.
Outputs
audioUri string
uriInternal storage URI of the primary audio
audioUris array
Internal storage URIs of the audio tracks
contentType string
MIME type of the primary file
status string
Sonilo task status
stemUris object
Internal storage URIs of separated stems, keyed by stream index and stem name
stemsError string
Stem separation warning
taskId string
Sonilo task identifier
title string
Generated title
