TIGER Audio Extractor

Tools

• TIGER_audio_extraction_separate_dialog_effects_music_from_audio Separate a mixed audio file into dialog, sound effects, and background music stems. Use this tool when an agent needs dialog/effects/music source separation from one uploaded audio file. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: tuple[str, str, str]: File paths for dialog-only audio, effects-only audio, and music-only audio., Raises:, RuntimeError: when a generated output file is missing or empty., Important:, Use this for dialog/effects/music separation, not for isolating individual speakers.
• TIGER_audio_extraction_separate_dialog_effects_music_from_video Separate a video's audio into dialog-only, effects-only, and music-only video outputs. Use this tool when an agent needs separate video copies with different audio stems. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: tuple[str, str, str]: File paths for dialog-audio video, effects-audio video, and music-audio video., Raises:, ValueError: when the uploaded video has no audio track., RuntimeError: when a generated output file is missing or empty., Important:, This preserves the original visuals and replaces only the audio track.
• TIGER_audio_extraction_separate_speakers_from_audio Separate overlapping speech in an audio file into individual speaker tracks. Use this tool when an agent needs to isolate speakers from a speech recording. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: list: Gradio updates containing separated speaker audio files and visibility states., Raises:, RuntimeError: when a generated output file is missing or empty., Important:, This tool separates speaker audio but does not transcribe, diarize, or identify speaker names.
• TIGER_audio_extraction_separate_speakers_from_video Separate speakers from a video's audio track and return speaker-specific videos. Use this tool when an agent needs to isolate speakers from a video while preserving visuals. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: list: Gradio updates containing separated speaker video files and visibility states., Raises:, ValueError: when the uploaded video has no audio track., RuntimeError: when a generated output file is missing or empty., Important:, This separates speakers but does not transcribe, diarize, or separate dialog from effects or music.

No tool matches.

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