infery
← All models

Mirelo SFX1.6

sfx1.6-inpaint-audio

Text to Speechby Mirelo AI

Erase and replace any moment in your audio with AI-driven precision.

Details

Accepts
audio

Pricing

Price
1.25 cr / second

Prices in credits (1 credit = $0.01).

Data schema

Input

FieldTypeDescription
seedSeed for generation. -1 or None for random.
segmentrequiredRegion [start_s, end_s] (in seconds, 1s ≤ start < end ≤ 10s, 1–8s span) to regenerate. The audio outside this region is preserved.
audio_urlrequiredstringURL 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.
num_samplesintegerNumber of variations to generate.
text_promptOptional text prompt guiding the regenerated segment.
upload_audio_formatstringenum: wav, mp3, aac, flacAudio format for the returned files.

Output

FieldTypeDescription
audioarraySource audio with the requested segment regenerated; audio outside the segment is preserved.