GET
/v1/schemas/fal/audio/mirelo-ai/sfx1.6/inpaint-audio
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace5a3a380cbb748ca322ee257e7a922f9b226f4b2763dfe529ac72fc814f0a6e38{
"fetchedAt": 1786770058,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
6 properties · 2 required · 1 $defs| property | type | description | constraints |
|---|---|---|---|
| audio_url* | string | 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. | |
| segment* | AudioSegmentSpec | Region [start_s, end_s] (in seconds, 1s ≤ start < end ≤ 10s, 1–8s span) to regenerate. The audio outside this region is preserved. | |
| seed | integer | Seed for generation. -1 or None for random. | -1 ≤ n ≤ 18446744073709552000 · nullable |
| upload_audio_format | enum | Audio format for the returned files. | wav | mp3 | aac | flac · default: "wav" |
| text_prompt | string | Optional text prompt guiding the regenerated segment. | nullable |
| num_samples | integer | Number of variations to generate. | 1 ≤ n ≤ 4 · default: 2 |
Types
1 $defsAudioSegmentSpecobject
Region of the input audio to replace, in seconds.
| start_s* | number | Start of the inpaint region in seconds. Must leave a 1s left gap (>= 1.0). | 1 ≤ n ≤ 9 |
| end_s* | number | End of the inpaint region in seconds. Must be <= 10.0. | 2 ≤ n ≤ 10 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"mirelo-ai/sfx1.6/inpaint-audio","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}