Audio

5 min

Nima allows you to automatically detect harmful audio content using the AI detection providers you have configured.

Example payload

{
    "priority": "high",
    "channel": "automated detection",
    "reason_for_request": "This audio contains bullying",
    "note": "facilis occaecati eos",
    "customerSpecific": {},
    "content": {
        "content_id": "saepe ut debitis",
        "title": "firearm",
        "body": "Pariatur illum modi sapiente sint et quae quo corporis. Odit minus quasi hic laboriosam minima et. Ex asperiores dicta.",
        "url": "https://res.cloudinary.com/dkfnrxfqd/video/upload/v1737952621/flac3_m5fnhz.flac",
        "language": "en",
        "token": "",
        "type": {
            "id": "AUDIO"
        },
        "status": "published",
        "customerSpecific": {
        
        }
    },
    "reportee": {
        "id": "t43YgUNcn_Fswra",
        "name": "Ms. Edgar Satterfield",
        "phoneNumber": "964-806-7414",
        "emailAddress": "[email protected]",
        "customerSpecific": {}
    },
    "location": {
        "city": "Lake Kileyville",
        "postalCode": "84",
        "region": "Madisynstad",
        "countryCode": "PT",
        "ipAddress": "176.107.49.70",
        "customerSpecific": {}
    },
    "label": [
        "weapon"
    ]
}

Request payload requirements

For audio moderation, ensure your request payload includes the following content-type specific requirements:

Attribute	Required	Description
content.url	Yes	For audio content, the URL should point to the audio file. Currently supported audio formats: MP3, MP4, WAV, FLAC
content.type.id	Yes	Must be set to "AUDIO"
content.language	No	ISO language code in lowercase (en, fr) for improved accuracy

For all other payload parameters, please refer to the Proactive DetectionProactive Detection documentation.

Configuring detection rules

To create a rule for automated audio detection, navigate to Configure > Trust & Safety > Rules and define the following conditions:

Required Conditions:

Channel: Must be set to "Proactive Detection"

Content Type: Must be set to "Audio"

Once these conditions are set, the list of available AI detection providers will be accessible via the Choose Provider button.

Audio-specific features

Audio visualization in moderation console

Once Nima receives a case containing audio content, it displays the content to moderators via the moderation console with an integrated audio player. The interface includes advanced features specifically designed for audio moderation:

Waveform Visualization: Highlights on the audio waveform where harmful content has been detected by the AI detection provider

Detected Vocabulary List: Lists detected harmful words or phrases along with their timestamps

Timestamp Navigation: Allows moderators to jump straight to the sections that triggered detection