Mirelo SFX1.6

POST/v1/run

Sfx1.6 Inpaint Audio by Mirelo - advanced AI model for audio-to-audio. Delivers high-quality results with fast inference, suitable for both creative and production workflows.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to mirelo/sfx1.6/inpaint-audio.

Default: mirelo/sfx1.6/inpaint-audio

Optional<string>audio

URL of the source audio. Maximum 10 seconds — longer clips are rejected. The model regenerates only the region defined by `segment`; everything outside it is preserved.

Optional<integer>seed

Seed for generation. -1 or None for random.

Range: -1 to ∞

Optional<string>text_prompt

Optional text prompt guiding the regenerated segment.

Optional<string>upload_audio_format

Audio format for the returned files.

Allowed values: wav, mp3, aac, flac

Default: wav

Optional<string>segment

Region [start_s, end_s] (in seconds, 1s ≤ start < end ≤ 10s, 1–8s span) to regenerate. The audio outside this region is preserved.

Optional<integer>num_samples

Number of variations to generate.

Range: 1 to 4

Default: 1

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

Allowed values: pending, running, completed, failed, timeout

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: audio-to-audio

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mirelo/sfx1.6/inpaint-audio",
  "audio": "https://static.sandbase.ai/examples/mirelo/sfx1.6/inpaint-audio/output_url_0.wav"
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/f3d2e8a1-7c4b-4a12-9d2e-123456789abc \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "f3d2e8a1-7c4b-4a12-9d2e-123456789abc",
  "model": "mirelo/sfx1.6/inpaint-audio",
  "status": "running"
}