cjwbw/audiosep
Separate a target sound from a mixed audio recording using a natural-language text query. Provide an audio file and a de...
Found 13 models (showing 1-13)
Separate a target sound from a mixed audio recording using a natural-language text query. Provide an audio file and a de...
Separate a target sound source from a mixed audio track using an example query audio. Takes a mixture audio and a short...
Generate original songs from a text theme with selectable mood, genre, and tempo, then receive the full mix plus isolate...
Separate music into stems from an audio file, outputting isolated vocals, drums, bass, and other, with optional guitar a...
Separate music into stems from an input audio file. Outputs isolated vocals, drums, bass, and other stems, plus instrume...
Analyze music to extract song structure, tempo (BPM), and downbeats, and optionally separate stems. Takes an audio file...
Separate music into stems from an input audio file. Leverage Demucs/MDX source separation to isolate vocals and accompan...
Separate music into stems from an audio input. Use a Demucs-based source separation model to output individual tracksβvo...
Separate vocals and instrumental accompaniment from an input audio track. Takes an audio file and returns two stems: iso...
Separate vocals and instruments from a song into isolated stems. Accepts a mixed audio track and extracts selected sourc...
Analyze music structure and separate stems from a music audio input. Uses Harmonix models for structure analysis and Dem...
Separate music into stems (vocals, drums, bass, guitar, piano, other) from an input audio file. Output isolated audio tr...
Create an RVC v2 voice cloning dataset from a YouTube video. Provide a YouTube URL and optionally a dataset name; it dow...