Nodes/ComfyUI-AudioMoodAnalyzer/Audio Mood Analyzer (Timeline)
ComfyUI Node

Audio Mood Analyzer (Timeline)

A ComfyUI node in audio/analysis with 17 inputs and 4 outputs.

By andrea-spoldi·Created 3 months ago·Updated 2 months ago· 0
Audio Mood Analyzer (Timeline)
  • audio
  • prompt_sequence_json
  • merge_prompts
  • environment_prompts
  • subject_prompt
ollama_urlhttp://localhost:11434/api/generate
modelqwen3:14b
analysis_temperature0.4
prompt_temperature0.8
custom_contextAnalyze the music as pure sound, not lyrics. Translate sonic qualities into emotional visual direction.
lyrics_or_text
focus_fragment
song_title
song_description
song_genre
style_presetpainterly
style_notes
n_segments8
generate_environment_prompttrue
generate_subject_prompttrue
generate_merge_prompttrue
Categoryaudio/analysis

Inputs (17)

NameTypeDefaultDescription
audioAUDIO
ollama_urlSTRINGhttp://localhost:11434/api/generate
modelSTRINGqwen3:14b
analysis_temperatureFLOAT0.40–1.5
prompt_temperatureFLOAT0.80–1.5
custom_contextSTRINGAnalyze the music as pure sound, not lyrics. Translate sonic qualities into emotional visual direction.
lyrics_or_textSTRING
focus_fragmentSTRING
song_titleSTRING
song_descriptionSTRING
song_genreSTRING
style_presetCOMBOpainterly5 options: painterly, cinematic, raw, abstract, custom
style_notesSTRING
n_segmentsINT82–32
generate_environment_promptBOOLEANtrue
generate_subject_promptBOOLEANtrue
generate_merge_promptBOOLEANtrue

Outputs (4)

NameTypeDescription
prompt_sequence_jsonSTRING
merge_promptsSTRING
environment_promptsSTRING
subject_promptSTRING