Configuration Reference

Every parameter maps directly to client.process().

Option reference

Audio cleaning

Option	Type	Default	Description
`fillers`	`boolean`	`false`	Remove "um", "uh", "like", and similar filler words
`long_silences`	`boolean`	`false`	Trim long pauses and gaps between sentences
`mouth_sounds`	`boolean`	`false`	Remove clicks, lip smacks, and tongue sounds
`breath`	`boolean \| string`	`false`	Remove audible breathing between sentences
`stutters`	`boolean`	`false`	Remove repeated word fragments ("I— I— I think")
`hesitations`	`boolean`	`false`	Remove short hesitation sounds that aren't full filler words
`muted`	`boolean`	`false`	Silence edits instead of cutting — preserves original timing

Filler and hesitation detection is language-aware. English, German, and Romanian have the most accurate models. See supported languages.

breath options:

Value	Behavior
`true`	Recommended for most audio. Best default for challenging recordings.
`"legacy"`	Conservative removal. Safer choice for already-clean recordings.
`"natural"`	Lighter touch — preserves more of the original breathing feel.
`false`	Disabled (default).

Audio enhancement

Option	Type	Default	Description
`remove_noise`	`boolean`	`true`	Reduce hiss, hum, fan noise, and background sounds. On by default; pass `false` to disable it.
`studio_sound`	`boolean \| string`	`false`	Aggressive enhancement for studio-quality output.
`normalize`	`boolean`	`false`	Balance volume levels throughout the file
`keep_music`	`boolean`	`false`	Preserve music sections during noise reduction
`autoeq`	`boolean`	`false`	Legacy automatic EQ option. Prefer `studio_sound`; `autoeq` will be removed in a future release.

studio_sound options:

Value	Behavior
`true`	Recommended. Applies aggressive studio-quality enhancement.
`"nightly"`	Advanced/experimental variant. Currently behaves similarly to `true`.
`false`	Disabled (default).

studio_sound is more aggressive than remove_noise. For most recordings, remove_noise alone is sufficient.

Output

Option	Type	Default	Description
`export_format`	`string`	`'auto'`	Audio-only output format: `'mp3'`, `'wav'`, `'flac'`, `'m4a'`, or `'auto'` (matches input). Video jobs keep the original video container format.
`target_lufs`	`number`	`-16`	Target integrated loudness in LUFS. `-16` is the standard for podcasts
`mute_lufs`	`number`	`-120`	Gate level for LUFS measurement. Default -120 disables gating.
`export_timestamps`	`boolean`	`false`	Return a JSON file with edit markers for use in a DAW or NLE

Content generation

Option	Type	Default	Description
`transcription`	`boolean`	`false`	Full word-by-word transcript. Language auto-detected.
`summarize`	`boolean`	`false`	Chapter markers, key learnings, and episode summary. Enables `transcription` automatically.
`social_content`	`boolean`	`false`	Generate tweets, LinkedIn posts, and show notes. Enables `summarize` automatically.

Delivery

Option	Type	Default	Description
`signed_url`	`string`	`undefined`	Pre-signed PUT URL. Cleanvoice uploads directly to your storage instead of hosting the file.

Advanced

Option	Type	Default	Description
`merge`	`boolean`	`false`	Multi-track only. Merge all tracks into a single output file. If you need automatic level balancing for a merged multi-track job, use `automix` as the companion option.
`audio_for_edl`	`boolean`	`false`	Video workflows only. Return additional uncut enhanced audio alongside the edited video for EDL/NLE work.
`video`	`boolean`	`false`	Process the input as video. The SDK auto-detects common video filenames and URLs, but explicit `video: true` is safest for ambiguous or extensionless URLs.

For raw REST requests, video must be set to true for actual video editing. Otherwise the file is treated as audio-only. In the SDK, common video paths are auto-detected, but being explicit is still safest.

Full example

import { Cleanvoice } from '@cleanvoice/cleanvoice-sdk';

const client = Cleanvoice.fromEnv();

const result = await client.process('episode.mp3', {
  remove_noise: true,
  studio_sound: true,
  normalize: true,
  fillers: true,
  long_silences: true,
  export_format: 'mp3',
  transcription: true,
});

console.log('Cleaned audio:', result.audio.url);
await result.audio.download('cleaned.mp3');

if (result.transcript) {
  console.log('Transcript:', result.transcript.text);
}

On this page