TIGER Audio Extractor

Tools

• TIGER_audio_extraction_separate_dnr Perform Dialog, Effects, and Music (DnR) separation on an uploaded audio file. Returns: Paths to the separated audio files:, Dialog-only audio (dialog.wav), Sound effects-only audio (effect.wav), Background music-only audio (music.wav), This function uses a pretrained DnR model (TIGER-DnR) to isolate the components in the audio., It is intended for tasks such as improving intelligibility or remixing.
• TIGER_audio_extraction_separate_dnr_video Separate dialog, effects, and music from the audio of an uploaded video file and reattach them to the original video. Returns: Paths to the output videos with:, Only dialog audio track (dialog_video.mp4), Only effects audio track (effect_video.mp4), Only music audio track (music_video.mp4), The audio is extracted from the video, separated using the DnR model, and then reattached to the original video visuals.
• TIGER_audio_extraction_separate_speakers Perform speaker separation on a mixed audio file containing multiple speakers. Returns: A list of Gradio update objects, each containing:, A separate audio file for each identified speaker (up to MAX_SPEAKERS), Visibility and label updates for the UI, This function internally calls a pretrained speech separation model (TIGER-speech), and isolates individual speaker tracks from the input audio.
• TIGER_audio_extraction_separate_speakers_video Separate individual speakers from the audio track of a video and reattach each speaker’s voice to a copy of the original video. Returns: A list of Gradio update objects each containing:, A new video file where the audio consists of only one speaker's voice, Visibility and label information for UI display, The function extracts audio from the video, separates individual speakers using a pretrained model,, and generates one video per speaker by replacing the audio in the original video.

No tool matches.

As the server's own listing gives them. We never call a tool.