What is Azure equivalent for input_audio_noise_reduction ?

Hello @Divjot Singh

Thank you for Reaching out to Microsoft Q&A.

At present, Azure OpenAI Realtime API does not expose a direct equivalent to OpenAI’s input_audio_noise_reduction parameter.

Why This Difference Exists

Although Azure OpenAI Realtime and OpenAI’s public Realtime API use the same underlying model family, the available API parameters are not always identical. New capabilities are often introduced in the OpenAI public API first and may be added to Azure OpenAI at a later stage.

input_audio_noise_reduction is one such parameter. It is currently available in OpenAI’s Realtime API, but it is not yet exposed as a configurable parameter in Azure OpenAI Realtime.

How Azure OpenAI Handles Audio Today

Azure OpenAI Realtime automatically performs baseline audio preprocessing as part of the service pipeline. This includes:

• Background noise suppression
• Audio normalization
• Input conditioning for improved transcription and response quality

This means that a standard level of noise handling is already applied automatically by the service, even though there is no customer-configurable toggle for it.

Options for Advanced Noise Reduction

If your application requires more aggressive or customizable noise suppression, the recommended approach is to preprocess the audio before sending it to Azure OpenAI.

1: Azure Speech SDK

If you are using the Azure Speech SDK for audio capture or speech processing, it includes built-in audio enhancement capabilities such as:

• Noise suppression
• Echo cancellation
• Automatic gain control

This is the recommended Microsoft-native solution for client-side audio preprocessing.

For example, the Speech SDK allows you to configure audio processing options before streaming audio to your application pipeline.

2: Azure Voice Live SDK

If you are using the Azure Voice Live SDK for real-time conversational scenarios, it provides an explicit setting for input noise reduction.

You can configure InputAudioNoiseReduction through VoiceLiveSessionOptions, allowing you to specify the desired level of noise suppression before audio is sent to the model.

In this case, the functionality is available at the SDK layer rather than directly through the Azure OpenAI Realtime API.

3: REST API or Custom Clients

If you are calling Azure OpenAI Realtime directly via REST or a custom WebSocket implementation, there is currently no server-side noise reduction parameter equivalent to input_audio_noise_reduction.

In this scenario, you should perform audio preprocessing locally before sending audio to Azure OpenAI. Common options include:

• Azure Speech SDK
• WebRTC built-in noise suppression
• Platform-native audio processing APIs
• Third-party DSP or audio enhancement libraries

Azure OpenAI Realtime API does not currently provide a direct equivalent to input_audio_noise_reduction.

Azure OpenAI automatically applies baseline noise suppression and audio conditioning.

For advanced or customizable noise reduction, audio should be preprocessed on the client side before being sent to Azure OpenAI.

Please refer this

Audio processing in Speech SDK: https://docs.microsoft.com/azure/ai-services/speech-service/audio-processing-overview#speech-sdk-integration

VoiceLiveSessionOptions.InputAudioNoiseReduction: https://learn.microsoft.com/dotnet/api/azure.ai.voicelive.voicelivesessionoptions.inputaudionoisereduction

Overview of Azure Speech service: https://docs.microsoft.com/azure/cognitive-services/speech-service/overview

I hope this helps, do let me know if you have further queries.

Thank you!

Hi @Divjot Singh,

Did you get any chance to review the above response. Do let me know if you have any further queries.

Thank you!