Stable Audio 3

Regenerate a selected region of an existing audio clip with Stability AI's stable-audio-3. Supply a source clip with audioUrl and a prompt describing what the masked region [mask_start, mask_end] should contain; the rest of the audio is preserved.

Supported Models

• stable-audio-3 — Stable Audio 3

Parameters

Parameter	Type	Required	Description
type	string	Yes	Must be "AUDIO_INPAINT"
model	string	Yes	Must be "stable-audio-3"
promptObject	object	Yes	Stable Audio inpaint parameters

Prompt Object Parameters

Parameter	Type	Required	Description
prompt	string	Yes	Description of the audio to generate in the masked region
audioUrl	string	Yes	Source audio clip to inpaint (S3 asset key — upload via the asset API first)
output_format	string (enum)	Yes	Output format. One of mp3, wav. Default mp3
mask_start	number	No	Start of the region (in seconds) to regenerate. min 0. Default 0
mask_end	number	No	End of the region (in seconds) to regenerate. min 0, max 380, and must be greater than mask_start. Default 30
duration	number	No	Total length of the output audio in seconds. min 1, max 190. Default 60
steps	number	No	Number of diffusion steps. Higher = more detail but slower. min 4, max 50. Default 8
cfg_scale	number	No	How closely the audio follows the prompt. min 1, max 15. Default 1
seed	number	No	Seed for reproducible results. 0 uses a random seed. min 0, max 4294967294

Interactive API Testing

API Playground

GETPOSTPUTDELETEhttps://api.1min.ai/api/features

Prompt *add a smooth saxophone solo over the existing backing track

Source Audio *

Mask Start (seconds)

Start of the region to regenerate

Mask End (seconds)

End of the region to regenerate. Must be greater than mask start

Duration (seconds)

1–190 seconds. Total length of the output audio

Output Format *MP3 - Compressed audio formatWAV - Uncompressed audio format

Steps

4–8. Higher = more detail but slower

Guidance Scale

1–15. Higher follows the prompt more closely

Seed (optional)

0 uses a random seed

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
  -H "API-KEY: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "AUDIO_INPAINT",
  "model": "stable-audio-3",
  "conversationId": "AUDIO_INPAINT",
  "promptObject": {
    "prompt": "add a smooth saxophone solo over the existing backing track",
    "audioUrl": "development/audios/source.mp3",
    "mask_start": 0,
    "mask_end": 30,
    "duration": 60,
    "output_format": "mp3",
    "steps": 8,
    "cfg_scale": 1
  }
}'

Response Format

Successful requests return an aiRecord echoing the submitted promptObject and a resultObject containing the inpainted audio file path.

{
  "aiRecord": {
    "uuid": "9f4a2b1e-6c3d-4f5e-9a8b-2d1c0e3f4a5b",
    "userId": "c937fbcc-fa8f-4565-a440-c4d87f56fcb2",
    "teamId": "a4e176b2-dabb-451e-9c58-62b451fa9630",
    "model": "stable-audio-3",
    "type": "AUDIO_INPAINT",
    "status": "SUCCESS",
    "createdAt": "2026-06-20T10:52:19.827Z",
    "aiRecordDetail": {
      "promptObject": {
        "prompt": "add a smooth saxophone solo over the existing backing track",
        "audioUrl": "development/audios/source.mp3",
        "mask_start": 0,
        "mask_end": 30,
        "duration": 60,
        "output_format": "mp3",
        "steps": 8,
        "cfg_scale": 1
      },
      "responseObject": {
        "finish_reason": "SUCCESS",
        "seed": 12345
      },
      "resultObject": [
        "development/audios/2026_06_20_17_52_25_414_538984.mp3"
      ]
    },
    "temporaryUrl": ""
  }
}