Skip to main content
POST
Transform audio (voice-changer, stem separation, video→audio extraction, …)
Voice changing, stem separation, extracting the audio from a video — the transformations that take audio in and give audio back, as opposed to speech synthesis or transcription.

Authorizations

Authorization
string
header
required

API key in format: Bearer inf_***

Body

application/json
model
string
required

Model ID to use for the transformation

audio_url
string

Source audio URL — required for audio-input models (voice-changer, demucs)

video_url
string

Source video URL — required for video-input models (video→audio extraction)

response_format
string

Requested output audio format (model-dependent; applied best-effort)

Response

Transformed audio result. url is the aggregator's own hosted output URL, or a private-storage signed URL (7-day expiry) when the provider only returns inline bytes.

created
integer
Example:

1713204900

data
object[]
credits_used
integer
Example:

40