Detector24
Back to Model Catalogue
Voice Safety Detection
AudioSpeech Analysis

Voice Safety Detection

Detect unsafe audio content including harassment, profanity, discrimination, and illegal content

Accuracy
86.5%
Avg. Speed
2.5s
Per Request
$0.0150
API Name
voice-safety-detection

API Reference

Version
2601
Jan 3, 2026
Avg. Processing
2.5s
Per Request
$0.015
Required Plan
trial

Input Parameters

Detects unsafe audio content including hate speech, harassment, profanity, and other toxicity

audio_urlstringRequired

URL of audio file to analyze for unsafe content

Example:
https://example.com/audio.mp3

Response Fields

Audio safety analysis with multi-category classification

is_unsafeboolean

True if unsafe content detected

Example:
false
discrimination_probabilityfloat

Probability of discrimination/hate speech (0.0-1.0)

Example:
0.02
harassment_probabilityfloat

Probability of harassment content (0.0-1.0)

Example:
0.03
sexual_probabilityfloat

Probability of sexual content (0.0-1.0)

Example:
0.01
illegal_probabilityfloat

Probability of illegal activity content (0.0-1.0)

Example:
0.01
dating_probabilityfloat

Probability of inappropriate dating content (0.0-1.0)

Example:
0.02
profanity_probabilityfloat

Probability of profanity (0.0-1.0)

Example:
0.05
max_probabilityfloat

Highest probability across all categories (0.0-1.0)

Example:
0.05
top_categorystring

Category with highest probability

Example:
safe

Complete Example

Request

{
  "model": "voice-safety-detection",
  "audio_url": "https://example.com/audio.mp3"
}

Response

{
  "success": true,
  "data": {
    "is_unsafe": false,
    "discrimination_probability": 0.02,
    "harassment_probability": 0.03,
    "sexual_probability": 0.01,
    "illegal_probability": 0.01,
    "dating_probability": 0.02,
    "profanity_probability": 0.05,
    "max_probability": 0.05,
    "top_category": "safe"
  }
}

Additional Information

Rate Limiting
If we throttle your request, you will receive a 429 HTTP error code along with an error message. You should then retry with an exponential back-off strategy, meaning that you should retry after 4 seconds, then 8 seconds, then 16 seconds, etc.
Supported Formats
mp3, wav, ogg, aac, m4a, flac
Maximum File Size
10MB
Tags:safetyharassmentprofanitydiscriminationaudiomoderation

Ready to get started?

Integrate Voice Safety Detection into your application today with our easy-to-use API.

Learn more about audio moderationBrowse all models