> For the complete documentation index, see [llms.txt](https://docs.ixhello.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ixhello.com/ixhc/noise-cancellation-for-real-time-voice-channel.md).

# Noise Cancellation for Real-Time Voice Channel

### **Overview:**

\
Integrate Third party noise cancellation technology into iX Hello Customer’s real-time voice channel to enhance **voice quality and user experience**. This integration ensures clear, uninterrupted voice communication between users and AI voicebots by filtering out background noise automatically.

#### **Feature Description:**

#### iX Hello Customer Voice Channel: Noise Suppression Integration

* The iX Hello Customer voice channel will integrate **third-party tools** via **SDKs/APIs** to enable AI-powered noise suppression for live voice interactions.
* Audio streams will be processed **in real time**, removing unwanted ambient sounds such as:
  * Background chatter
  * Keyboard typing
  * Fan noise
  * Other environmental disturbances
* Only **clear, natural human speech** will be transmitted to participants.
* The noise cancellation feature will operate **seamlessly within the existing real-time voice flow**, ensuring:
  * No perceptible latency
  * No impact on system performance
* Users will have the ability to **configure noise cancellation options** at the **bot level**, based on:
  * Performance requirements
  * Use-case preferences

### Why Third-Party Tool in RTC? <a href="#why-krisp-in-rtc" id="why-krisp-in-rtc"></a>

#### Advanced Features for Optimal Audio Processing

* Superior Noise Cancellation: Utilizes neural network processing to effectively eliminate background noise such as traffic, typing, and barking dogs.
* Voice Preservation: Ensures natural speech quality by maintaining clarity without introducing artifacts.
* Real-Time Processing: Engineered for low-latency telephony with 20ms frame optimization.
* VAD-Integration: Incorporates built-in Voice Activity Detection to enhance OpenAI speech recognition accuracy.
* Adaptive Thresholds: Automatically adjusts VAD sensitivity to noise level variations, ensuring consistent performance.

#### **Key Capabilities:** Real-Time Audio Processing Features

* Noise Cancellation: Effectively apply noise cancellation to user audio streams for improved clarity.
* SDK/API Integration: Seamlessly integrate third-party tools within the iXHC Real-Time Channel.
* Low-Latency Processing: Maintain natural conversation flow with minimal delay.
* Bot-Level Configuration: Easily configurable settings tailored to individual bots.
* Azure OpenAI Compatibility: Ensure full compatibility with Azure OpenAI's real-time streaming architecture.
* Secure Processing: Conduct secure, on-device or in-stream processing without storing raw audio or sharing with third parties.

### **How It Works**

* Audiorouting: iX Hello routes microphone input through the Third-Party Tool.
* Noise Suppression: Tool's AI filters out non-human sounds, by enabling the Noise Reduction toggle button
* Real-Time Output: Clean audio is transmitted instantly to the other participant.

<figure><img src="https://1107164708-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M8XHvUsfyTUFLvToHqD%2Fuploads%2Fx0p241bkQHWcAQuLcQ5S%2Fimage.png?alt=media&amp;token=75009ef6-a928-4f6e-865a-eef16d8396c1" alt="" width="443"><figcaption></figcaption></figure>

### **Key Benefits**

* Crystal-Clear Audio: Removes background noise from both ends of the call.
* Seamless Integration: Works within iX Hello without additional complexity.
* Privacy First: Audio processed locally; no data stored or transmitted externally.
* Low Latency: Maintains real-time communication quality


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.ixhello.com/ixhc/noise-cancellation-for-real-time-voice-channel.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
