ComfyUI Node
FLOAT Audio Feature Extract (VA)
Processes a batch of pre-validated (mono, correct SR) audio. It applies the feature extractor from the loaded Wav2Vec pipe, runs the audio through the Wav2Vec model, and interpolates the resulting features to match the target video FPS, making them ready for projection.
FLOAT Audio Feature Extract (VA)
- audio
- wav2vec_pipe
- wav2vec_features
- audio_num_frames
- processed_audio_features
- wav2vec_pipe_out
- audio
- fps
◄target_fps25.0►
◄only_last_featuresfalse►
CategoryFLOAT/Very Advanced
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| audio | AUDIO | The raw ComfyUI audio input. Must be mono and have the correct sample rate required by the Wav2Vec pipe. | |
| wav2vec_pipe | WAV2VEC_PIPE | The loaded Wav2Vec pipe, containing the model, feature extractor, and options. | |
| target_fps | FLOAT | 25.0 | The target video frames-per-second. Used to calculate the final number of feature frames. |
| only_last_features | BOOLEAN | false | If True, use only the features from the last transformer layer. If False, concatenate features from all transformer layers, resulting in a much larger feature dimension. |
Outputs (6)
| Name | Type | Description |
|---|---|---|
| wav2vec_features | TORCH_TENSOR | — |
| audio_num_frames | INT | — |
| processed_audio_features | TORCH_TENSOR | — |
| wav2vec_pipe_out | WAV2VEC_PIPE | — |
| audio | AUDIO | — |
| fps | FLOAT | — |