ComfyUI Node: Audio Recorder

Audio Recorder:

The SparkTTS_AudioRecorder is a specialized node designed for audio recording and processing within the ComfyUI environment. Its primary function is to capture audio input and enhance its quality by applying various audio processing techniques. This node is particularly beneficial for users who need to record audio with minimal noise and echo, ensuring a clean and clear output. By leveraging advanced methods such as spectral gating and noise profiling, the SparkTTS_AudioRecorder effectively reduces unwanted noise and echoes, resulting in a more polished audio recording. This makes it an invaluable tool for AI artists and developers working on projects that require high-quality audio input, such as voice cloning or audio synthesis.

Audio Recorder Input Parameters:

recording

This parameter indicates whether the audio recording process should be initiated. It is a boolean value where True starts the recording, and False skips the process. This parameter is crucial as it controls the execution of the audio recording function.

recording_duration

This parameter specifies the length of time, in seconds, for which the audio should be recorded. It directly impacts the duration of the captured audio and should be set according to the user's needs. There is no explicit minimum or maximum value provided, but it should be a positive integer.

noise_threshold

The noise threshold parameter determines the sensitivity of the noise reduction process. It is used to set the level at which the noise is considered significant enough to be removed. A higher threshold may result in more aggressive noise reduction, potentially affecting the quality of the desired audio, while a lower threshold may leave some noise in the recording.

smoothing_kernel_size

This parameter defines the size of the kernel used for smoothing the mask applied during the spectral gating process. It affects how smooth the transitions are in the noise reduction process. A larger kernel size results in smoother transitions but may also blur some audio details.

sample_rate

The sample rate parameter specifies the number of samples per second used in the audio recording. It is an integer value that affects the quality and size of the audio file. Common sample rates include 44100 Hz for CD-quality audio. The sample rate should be chosen based on the desired audio quality and the capabilities of the recording device.

Audio Recorder Output Parameters:

final_audio

The final_audio output is a dictionary containing the processed audio waveform and its sample rate. The waveform is a tensor representing the audio data, and the sample rate is an integer indicating the number of samples per second. This output is crucial as it provides the cleaned and enhanced audio ready for further use or analysis.

Audio Recorder Usage Tips:

• Ensure that the recording environment is as quiet as possible to minimize the initial noise level, which will improve the effectiveness of the noise reduction process.
• Adjust the noise_threshold parameter carefully to balance between noise reduction and audio quality. Test different values to find the optimal setting for your specific recording conditions.
• Use a sample rate that matches the quality requirements of your project. Higher sample rates provide better audio quality but result in larger file sizes.

Audio Recorder Common Errors and Solutions:

Audio processing failed: <error_message>

• Explanation: This error occurs when there is an issue during the audio processing phase, which could be due to incorrect parameter values or unexpected input data.
• Solution: Check all input parameters for correctness, ensure that the recording environment is suitable, and verify that the sample rate is supported by your hardware. If the problem persists, review the error message for specific details and adjust the parameters accordingly.