diff --git a/electron/native/wgc-capture/src/audio_sample_utils.cpp b/electron/native/wgc-capture/src/audio_sample_utils.cpp
index a8058c9..c816fea 100644
--- a/electron/native/wgc-capture/src/audio_sample_utils.cpp
+++ b/electron/native/wgc-capture/src/audio_sample_utils.cpp
@@ -100,6 +100,17 @@ bool sameAudioFormatForMixing(const AudioInputFormat& left, const AudioInputForm
            left.avgBytesPerSec == right.avgBytesPerSec;
 }
 
+AudioInputFormat makeAacCompatibleAudioFormat(const AudioInputFormat& source) {
+    AudioInputFormat format{};
+    format.subtype = MFAudioFormat_PCM;
+    format.sampleRate = source.sampleRate > 0 ? source.sampleRate : 48000;
+    format.channels = 2;
+    format.bitsPerSample = 16;
+    format.blockAlign = format.channels * (format.bitsPerSample / 8);
+    format.avgBytesPerSec = format.sampleRate * format.blockAlign;
+    return format;
+}
+
 void copyAudioWithGain(
     const BYTE* source,
     DWORD byteCount,
diff --git a/electron/native/wgc-capture/src/audio_sample_utils.h b/electron/native/wgc-capture/src/audio_sample_utils.h
index 81fc62d..4e61252 100644
--- a/electron/native/wgc-capture/src/audio_sample_utils.h
+++ b/electron/native/wgc-capture/src/audio_sample_utils.h
@@ -13,6 +13,7 @@
 #include <vector>
 
 bool sameAudioFormatForMixing(const AudioInputFormat& left, const AudioInputFormat& right);
+AudioInputFormat makeAacCompatibleAudioFormat(const AudioInputFormat& source);
 void copyAudioWithGain(
     const BYTE* source,
     DWORD byteCount,
diff --git a/electron/native/wgc-capture/src/main.cpp b/electron/native/wgc-capture/src/main.cpp
index ad46837..f8f56cd 100644
--- a/electron/native/wgc-capture/src/main.cpp
+++ b/electron/native/wgc-capture/src/main.cpp
@@ -410,6 +410,7 @@ int main(int argc, char* argv[]) {
     WasapiLoopbackCapture loopbackCapture;
     WasapiLoopbackCapture microphoneCapture;
     const AudioInputFormat* audioFormat = nullptr;
+    AudioInputFormat encoderAudioFormat{};
     AudioInputFormat systemAudioFormat{};
     AudioInputFormat microphoneAudioFormat{};
     if (config.captureSystemAudio) {
@@ -443,6 +444,12 @@ int main(int argc, char* argv[]) {
                       << jsonEscape(wideToUtf8(microphoneCapture.selectedDeviceName())) << "\"";
         }
         std::cout << "}" << std::endl;
+        encoderAudioFormat = makeAacCompatibleAudioFormat(*audioFormat);
+        std::cout << "{\"event\":\"encoder-audio-format\",\"schemaVersion\":2,\"sampleRate\":"
+                  << encoderAudioFormat.sampleRate
+                  << ",\"channels\":" << encoderAudioFormat.channels
+                  << ",\"bitsPerSample\":" << encoderAudioFormat.bitsPerSample
+                  << "}" << std::endl;
     }
 
     MFEncoder encoder;
@@ -454,7 +461,7 @@ int main(int argc, char* argv[]) {
             bitrate,
             session.device(),
             session.context(),
-            audioFormat)) {
+            audioFormat ? &encoderAudioFormat : nullptr)) {
         std::cerr << "ERROR: Failed to initialize Media Foundation encoder" << std::endl;
         return 1;
     }
@@ -579,9 +586,9 @@ int main(int argc, char* argv[]) {
         }
 
         audioMixer = std::make_unique<AudioMixer>(
-            *audioFormat,
-            config.captureSystemAudio ? systemAudioFormat : *audioFormat,
-            config.captureMic ? microphoneAudioFormat : *audioFormat,
+            encoderAudioFormat,
+            config.captureSystemAudio ? systemAudioFormat : encoderAudioFormat,
+            config.captureMic ? microphoneAudioFormat : encoderAudioFormat,
             config.captureSystemAudio,
             config.captureMic,
             config.microphoneGain,
diff --git a/electron/native/wgc-capture/src/mf_encoder.cpp b/electron/native/wgc-capture/src/mf_encoder.cpp
index de9220f..b56386e 100644
--- a/electron/native/wgc-capture/src/mf_encoder.cpp
+++ b/electron/native/wgc-capture/src/mf_encoder.cpp
@@ -1,5 +1,7 @@
 #include "mf_encoder.h"
 
+#include "audio_sample_utils.h"
+
 #include <mfapi.h>
 #include <mferror.h>
 #include <propvarutil.h>
@@ -156,7 +158,7 @@ bool MFEncoder::configureAudioStream(const AudioInputFormat& audioFormat) {
         return false;
     }
 
-    const UINT32 bitsPerSample = std::max<UINT32>(8, audioFormat.bitsPerSample);
+    const AudioInputFormat encoderFormat = makeAacCompatibleAudioFormat(audioFormat);
     const UINT32 aacBytesPerSecond = 24'000;
 
     Microsoft::WRL::ComPtr<IMFMediaType> outputType;
@@ -165,7 +167,7 @@ bool MFEncoder::configureAudioStream(const AudioInputFormat& audioFormat) {
     }
     outputType->SetGUID(MF_MT_MAJOR_TYPE, MFMediaType_Audio);
     outputType->SetGUID(MF_MT_SUBTYPE, MFAudioFormat_AAC);
-    setAudioFormat(outputType.Get(), audioFormat.channels, audioFormat.sampleRate, 16);
+    setAudioFormat(outputType.Get(), encoderFormat.channels, encoderFormat.sampleRate, 16);
     outputType->SetUINT32(MF_MT_AUDIO_AVG_BYTES_PER_SECOND, aacBytesPerSecond);
     outputType->SetUINT32(MF_MT_AAC_PAYLOAD_TYPE, 0);
 
@@ -178,10 +180,10 @@ bool MFEncoder::configureAudioStream(const AudioInputFormat& audioFormat) {
         return false;
     }
     inputType->SetGUID(MF_MT_MAJOR_TYPE, MFMediaType_Audio);
-    inputType->SetGUID(MF_MT_SUBTYPE, audioFormat.subtype);
-    setAudioFormat(inputType.Get(), audioFormat.channels, audioFormat.sampleRate, bitsPerSample);
-    inputType->SetUINT32(MF_MT_AUDIO_BLOCK_ALIGNMENT, audioFormat.blockAlign);
-    inputType->SetUINT32(MF_MT_AUDIO_AVG_BYTES_PER_SECOND, audioFormat.avgBytesPerSec);
+    inputType->SetGUID(MF_MT_SUBTYPE, encoderFormat.subtype);
+    setAudioFormat(inputType.Get(), encoderFormat.channels, encoderFormat.sampleRate, encoderFormat.bitsPerSample);
+    inputType->SetUINT32(MF_MT_AUDIO_BLOCK_ALIGNMENT, encoderFormat.blockAlign);
+    inputType->SetUINT32(MF_MT_AUDIO_AVG_BYTES_PER_SECOND, encoderFormat.avgBytesPerSec);
     inputType->SetUINT32(MF_MT_ALL_SAMPLES_INDEPENDENT, TRUE);
 
     if (!succeeded(sinkWriter_->SetInputMediaType(audioStreamIndex_, inputType.Get(), nullptr),