CleanvoiceDocs
REST API

Edit Settings

Recommended presets for common use cases.

Not sure which options to enable? Pick a preset below and drop the config into your request body.

For the full list of every option with types and defaults, see the Configuration Reference.

Best for: audio-quality improvements only — no transcript, no speech edits.

Removes background noise and normalises loudness. Language-agnostic.

{
  "config": {
    "remove_noise": true,
    "normalize": true
  }
}

Best for: podcasts, voiceovers, or interviews where you want a professional mic sound.

Noise removal plus AI studio enhancement — tightens room reverb and adds mic presence.

{
  "config": {
    "remove_noise": true,
    "studio_sound": true,
    "normalize": true
  }
}

Best for: spoken-word recordings where you want automatic filler and silence removal.

Removes filler words, long silences, mouth sounds, breathing, and stutters.

{
  "config": {
    "fillers": true,
    "long_silences": true,
    "mouth_sounds": true,
    "breath": true,
    "stutters": true,
    "remove_noise": true,
    "normalize": true
  }
}

Best for: when you need the text but don't want to touch the audio.

Generates a transcript without editing the file. Set transcription to true and let Cleanvoice auto-detect the spoken language.

{
  "config": {
    "transcription": true
  }
}

Best for: content pipelines that need a transcript, summary, and social copy in one pass.

Returns a transcript, an AI-generated summary, and social media content suggestions.

{
  "config": {
    "transcription": true,
    "summarize": true,
    "social_content": true
  }
}