Conversational AI

Krisp Server SDK is integrated into the audio pipeline on servers to clean background noises and voices from audio streams. For example, putting Krisp NC before Voice Activity Detection (VAD) in the audio pipeline results in much better “turn detection” (aka “unwanted interruptions”) for Conversational AI applications.

Use Cases

• Conversational AI
• Speech-to-Speech models
• AI Voice Agents

Multiple Audio Stream Support

Krisp SDK supports the real-time processing of multiple audio streams using a single model loaded into memory, ensuring efficient memory utilization.

Demo

Demo with Daily using Pipecat and Google Gemini Live

Recommended Models

Krisp offers different noise cancellation models optimized for different use cases, as shown in the following table.

• NC (noise cancellation) models remove background noises and background chatter.
• BVC (background voice cancellation) models remove background noises and keep only the primary speaker's voice. The model requires that the user speak close to the microphone.

Automatic Resampling

Krisp Audio SDK will automatically resample the audio input to match the sampling rate of the model.

*The input and output 48kHz sampling rate of the stream is configurable.
*The 32kHz working sampling of the model depends on the selected model.

• The audio is resampled to the operational sampling rate of the model.
• The audio is processed using the AI model at the operational sampling rate.
• The audio is resampled back to the original sampling rate.