Skip to content

Audio Data Upload

The platform supports audio file uploads for biodiversity monitoring and analysis. Audio files are processed using AI/ML models to detect species and calculate acoustic indices.

Step 1: Navigate to Deployment

  • Select your project and site
  • Go to the deployment section where audio devices are configured
  • Ensure you have a deployment created for your site

Step 2: Upload Audio Files

  1. Click on "Upload Audio" button
  2. Select audio files from your device
  3. Supported formats: WAV, MP3, M4A, WEBM
  4. Maximum 20 files per upload
  5. Each file must be:
  6. Under 25 MB in size
  7. Maximum 5 minutes duration

Step 3: Processing

  • Files are automatically uploaded to Google Cloud Storage
  • Inference processing begins automatically or can be triggered manually
  • Processing typically completes within minutes for small files
  • Results include:
  • Species detections with confidence scores
  • Acoustic indices (ACI, ADI, BI, AEI, NDSI)
  • Spectrogram generation

Step 4: View Results

  • Access inference results from the deployment dashboard
  • View spectrograms and species detection predictions
  • Analyze acoustic indices trends over time
  • Filter results by species, date, or confidence level
Note: For detailed API instructions on uploading audio files, refer to the Upload Audio Files section of the Biodiversity Dashboard API documentation.

Upload Limits

Limit Type Value
Max files per request 20
Max file size 25 MB per file
Max duration 300 seconds (5 minutes) per file
Supported formats WAV, MP3, M4A, WEBM

Next Steps