Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.blackbox.dasha.ai/llms.txt

Use this file to discover all available pages before exploring further.

Filter out background noise from incoming audio so your agent hears speech clearly — even when callers are in noisy environments. Uses Krisp’s AI-powered noise suppression engine. What you’ll learn: How to enable noise suppression, configure suppression levels, and choose recording strategies.
Krisp noise suppression incurs an additional per-minute fee.

​
When to use noise suppression

EnvironmentWithout suppressionWith suppression
Street/trafficAgent mishears words, frequent “could you repeat that”Clear speech isolation
Cafe/restaurantBackground chatter confuses STTVoice stands out from ambiance
Construction siteHeavy machinery drowns out callerSpeech remains intelligible
Home with kids/petsBarking, crying triggers false transcriptionsFocuses on primary speaker
Noise suppression improves speech-to-text accuracy by removing non-voice audio before it reaches the transcription engine.

​
Configure noise suppression

  1. Open your agent’s configuration
  2. Navigate to the Features tab
  3. Find Noise Suppression and toggle it on
  4. Select Krisp as the engine
  5. Adjust the suppression level (0–100)
  6. Choose recording strategy (raw or cleaned)
  7. Save your agent

​
Configuration options

FieldTypeDefaultDescription
isEnabledbooleanfalseMaster toggle for noise suppression
typestring"none"Engine: "none" or "krisp"
noiseSuppressionLevelinteger75Aggressiveness (0–100)
recordWriteStrategystring"raw"What to save: "raw" or "cleaned"

​
Suppression levels

The noiseSuppressionLevel controls how aggressively background noise is filtered:
LevelEffectBest for
0–30Light filteringQuiet environments with occasional noise
40–60Moderate filteringOffice or home settings
70–85Strong filteringBusy public spaces (default: 75)
90–100Maximum filteringExtremely noisy environments
Very high levels (90+) may slightly affect voice quality. Start at 75 and adjust based on your use case.

​
Recording strategy

Choose what audio gets saved in call recordings:
StrategySavesUse when
rawOriginal unprocessed audioYou need the authentic recording for compliance or disputes
cleanedNoise-suppressed audioYou want cleaner recordings for review or training
noiseSuppression: {
  isEnabled: true,
  type: 'krisp',
  noiseSuppressionLevel: 75,
  recordWriteStrategy: 'raw'  // Keep original audio for legal purposes
}

noiseSuppression: {
  isEnabled: true,
  type: 'krisp',
  noiseSuppressionLevel: 80,
  recordWriteStrategy: 'cleaned'  // Save the cleaned version
}

​
How it works

  1. Caller audio arrives with background noise
  2. Krisp engine processes the audio in real-time
  3. Cleaned audio goes to STT for accurate transcription
  4. Recording saves either raw or cleaned audio (your choice)
The agent always hears the cleaned audio. The recording strategy only affects what gets stored.

​
Troubleshooting

​
Agent still mishearing in noisy environments

SymptomFix
Suppression enabled but no improvementVerify type is set to "krisp", not "none"
Some noise gets throughIncrease noiseSuppressionLevel to 85–90
Extreme noise environmentsLevel 100 + consider if call quality is viable

​
Voice sounds distorted

SymptomFix
Voice sounds robotic or thinLower noiseSuppressionLevel to 60–70
Words getting cut offReduce level; aggressive filtering can clip speech

​
Next steps

Ambient Noise

Add background sounds (outgoing)

Voice & Speech

Configure STT and TTS

Language Switching

Support multiple languages

Call Inspector

Debug call audio issues