Zum Inhalt
HALOWERK

Medienwerk

voice clean

Takes an audio or video file and returns a cleaned speech recording. A high-pass filter removes rumble and mains hum, an FFT noise reducer with continuous noise tracking lowers steady background noise such as fans, air conditioning and hiss by 10, 18 or 28 dB, a declicker removes short clicks, and the result is normalised to the target loudness in two passes. Noise floor, RMS level and integrated loudness are measured on the input and again on the output and returned, so the improvement is a.

POST https://medien.halowerk.com/v1/voice-clean

Eingaben

Felder des veröffentlichten Eingabeschemas
FeldTypPflichtBeschreibung
sourceobjectJaThe recording. Either url or content_base64.
duration_minutesintegerJaLength in started minutes — this is what you are billed for.
strengthstringNein
target_lufsnumberNein
output_formatstringNein
monobooleanNeinMix to one channel. Speech is almost always mono, and it halves the size.
Vollständiges Eingabeschema anzeigen
{
  "type": "object",
  "required": [
    "source",
    "duration_minutes"
  ],
  "additionalProperties": false,
  "properties": {
    "source": {
      "type": "object",
      "additionalProperties": false,
      "description": "The recording. Either url or content_base64.",
      "properties": {
        "url": {
          "type": "string",
          "maxLength": 2048
        },
        "content_base64": {
          "type": "string",
          "maxLength": 12000000
        },
        "filename": {
          "type": "string",
          "maxLength": 260
        }
      }
    },
    "duration_minutes": {
      "type": "integer",
      "minimum": 1,
      "maximum": 30,
      "description": "Length in started minutes — this is what you are billed for."
    },
    "strength": {
      "type": "string",
      "enum": [
        "light",
        "medium",
        "strong"
      ],
      "default": "medium"
    },
    "target_lufs": {
      "type": "number",
      "minimum": -30,
      "maximum": -10,
      "default": -16
    },
    "output_format": {
      "type": "string",
      "enum": [
        "opus",
        "mp3",
        "wav",
        "flac"
      ],
      "default": "opus"
    },
    "mono": {
      "type": "boolean",
      "default": true,
      "description": "Mix to one channel. Speech is almost always mono, and it halves the size."
    }
  }
}

Originalschema öffnen

Ergebnis & Dokumentation

Maschinenlesbare Dokumentation dieses Hubs

Quelle dieser Seite: der veröffentlichte HALOWERK-Katalog. Stand: 2026-11-01, 15:19 UTC.

Weitere Endpunkte dieses Hubs

Alle Endpunkte dieses Hubs →