Accent Conversion Server SDK is designed to run on Linux servers.

The SDK comes with various language bindings such as Python, Node.js, Go, Rust.

You can also directly use the default C++ SDK.

The SDK runs your servers (CPU) and audio data never leaves your machines.

Supported Platforms

Linux (armv8a, x64)

Code Snippet

import krisp_audio

# initialize Krisp SDK global instance
krisp_audio.globalInit("")

# Create Noise Cleaner with the specified configuration
nc_cfg = krisp_audio.NcSessionConfig()
ncFloat = krisp_audio.NcFloat.create(nc_cfg)

# Noise Cleaner frame by frame processing of the given audio stream
for i in range(0, 1000) # frame count
    processed_frame = ncFloat.process(frame, self.suppression_level)

# Free the Krisp SDK global instance
ncFloat = None
krisp_audio.globalDestroy()

try
{
    globalInit(L"");

    ModelInfo ncModelInfo;
    ncModelInfo.path = L"/path/to/the/ac-model.kef";

    NcSessionConfig ncCfg =
    {
        inRate,
        frameDurationMillis,
        outRate,
        &ncModelInfo,
        false,
        nullptr
    };

    std::shared_ptr<Nc<SamplingFormat>> ncSession = Nc<SamplingFormat>::create(ncCfg);

    while(frameAvailable)
    {
        ncSession->process(inFrame, inFrameSize, outFrame, outFrameSize);
    }

    // ncSession should be released before globalDestroy()
    ncSession.reset();
    globalDestroy();
}
catch(std::exception& ex)
{
  // Handle exception
}