Skip to main content

Documentation Index

Fetch the complete documentation index at: https://doc.rapida.ai/llms.txt

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

Noise cancellation removes background audio before Rapida runs Voice Activity Detection and Speech-to-Text. It helps prevent false speech detection and improves transcription quality when users speak from phones, shared offices, vehicles, cafes, or other noisy environments.
Noise cancellation is configured in Voice Input under Show advanced settings. It is part of the deployment voice configuration, so each deployment can use its own setting.

Provider

Rapida exposes RNNoise as the standard noise cancellation provider. RNNoise is designed for real-time speech enhancement. It reduces steady background noise while preserving speech intelligibility, making it a good default for phone calls and browser microphone sessions.
ProviderBest forNotes
RNNoisePhone calls, office noise, keyboard noise, light traffic, cafesDefault choice for most voice deployments.

When to use it

Enable noise cancellation when:
  • Calls happen over PSTN or mobile networks.
  • Users may be in offices, stores, vehicles, cafes, or shared spaces.
  • VAD triggers on background audio.
  • STT receives noisy audio and produces unstable transcripts.
  • You want one safer default across many caller environments.
You may disable or avoid it when:
  • Audio is already clean studio-quality input.
  • Another upstream system already performs strong noise suppression.
  • You hear speech artifacts after enabling it.
  • The STT provider performs better with untouched audio in your test calls.
Do not use noise cancellation to hide poor microphone placement, severe clipping, or echo. It can reduce background noise, but it cannot recover speech that was not captured clearly.

How it affects the pipeline

ComponentEffect
VADCleaner audio reduces false speech starts from background noise.
STTCleaner speech can improve transcript stability and word accuracy.
EOSBetter VAD activity signals make turn detection more predictable.
TTSNo direct effect. TTS happens after the assistant generates text.

Tuning with VAD

Noise cancellation and VAD should be tuned together.
SymptomWhat to adjust
Background noise interrupts assistant speechKeep RNNoise enabled and raise VAD threshold.
Quiet speakers are missedKeep RNNoise enabled, then lower VAD threshold slightly.
Words are clipped at the startLower VAD threshold or reduce minimum speech frames.
Speech gets split into multiple chunksIncrease VAD minimum silence frames.
See Voice Activity Detection for VAD provider and threshold details.

Channel guidance

ChannelRecommendation
Phone CallEnable RNNoise by default. Phone audio is often compressed, narrowband, and noisy.
Web WidgetEnable RNNoise when users may speak from uncontrolled environments.
Web App / SDKEnable RNNoise for support, sales, healthcare, field, or accessibility workflows. Test clean in-app microphone flows before deciding.

Troubleshooting

SymptomLikely causeWhat to do
Transcript includes background words or soundsNoise cancellation off or VAD too sensitiveEnable RNNoise and raise VAD threshold.
User speech sounds processed or thinNoise suppression too aggressive for the inputTest with RNNoise disabled for clean microphones.
Assistant still interrupts on noiseVAD threshold too lowRaise VAD threshold after enabling RNNoise.
STT accuracy is still poorWrong language/model, bad input audio, or clipped speechCheck Speech-to-Text and VAD settings.

Voice Pipeline Overview

Understand where noise cancellation sits in the full pipeline.

Voice Activity Detection

Tune speech detection after noise cancellation.

Speech-to-Text

Choose the transcription provider and model.

End of Speech Detection

Tune turn completion after VAD and STT.