Audio

Clean the voice: background noise, hum and echo

A video or audio file in, the same file out with its sound cleaned and its picture copied untouched (no re-encode). Background noise — air conditioners, fans, street, café chatter, wind, keyboards, room echo — is reduced with DeepFilterNet 3; 50/60 Hz mains hum is notched out; the voice is gently enhanced (high-pass, de-esser, compressor, presence) only where a measurement calls for it, and set to −16 LUFS. denoise: auto (default) measures the noise first and leaves a clean recording or a music bed as it is. The render's voice reports the noise found (its level against the voice and its kind), how far it was reduced and every step applied.

Billing: Per second of the file at the audio rate (the picture is copied, not rendered) + the voice clean-up per second, only when noise was reduced or the voice enhanced. Failed renders are not charged. · Rate limit: 30/min · Asynchronous

post/v1/studio/clean-audio

Request

  • Base URL: https://apihub.co.il
  • URL: https://apihub.co.il/v1/studio/clean-audio
  • Auth: HTTP bearer

Headers

Idempotency-Keystring

Replay-safe: the same execution is returned instead of charging twice

X-Tagstring

Group calls into one job (e.g. one video) — see GET /v1/usage?tag=…

x-wait-msinteger

Wait for the job inside this call (ms)

Request body

format'mp4' | 'mov' | 'webm' | 'mp3' | 'wav' | 'm4a'

The container to write (default: the file's own; another container gets mp4 for video, m4a for audio). The picture is copied as it is

denoise'off' | 'auto' | 'light' | 'strong'

Background-noise reduction (DeepFilterNet 3) — default off on edit / short / remove-silence, auto on clean-audio: auto measures the noise and reduces it only when there is some (a clean recording, a music bed or digital silence stays as it is) · light a gentle fixed reduction · strong as much as the model removes · off the sound as recorded. Mains hum (50/60 Hz) is notched out whenever it is found

enhanceboolean

Gentle voice enhancement after the noise: a high-pass at 75 Hz, a de-esser, a 3:1 compressor and a small presence lift — each only when the measurement calls for it (a clean studio voice stays as it is)

normalizeboolean

Set the cleaned sound to −16 LUFS, the social-media standard, with peaks under −1 dBTP

video_urlstring uri required

Public URL of the video or audio file (mp4, mov, webm, mp3, wav, m4a, ogg…) — or the url of a previous render

Response

Completed (or 202 while processing)

idstring

Execution id — stable across internal retries; use it with GET /v1/executions/{id}

status'pending' | 'processing' | 'completed' | 'partial' | 'failed' | 'cancelled' | 'timeout'
operationstring
tagstring nullable

Your X-Tag, if sent

created_atstring date-time
completed_atstring date-time nullable
outputobject

Operation result (see each operation). While a Studio render is processing: stage (queued · transcribing · downloading · preparing · cleaning_voice · mixing_audio · rendering · finishing), phase (the engine's: download · prepare · voice · audio · encode · qa · upload, or null), progress (a percent, 0–100) and progress_fraction (0–1), eta_seconds (seconds left, never below 0) and estimate_seconds

errorstring nullable

Changes

No recorded changes to this operation across all 2 revisions of this API.