
zsxkib/audio-flamingo-3
Answer questions about audio with text output, performing step-by-step reasoning across speech, music, and sound effects...
Found 15 models (showing 1-15)
Answer questions about audio with text output, performing step-by-step reasoning across speech, music, and sound effects...
Generate text descriptions and analyses of audio from an audio file and a guiding prompt. Produce free-form captions, ge...
Generate natural-language descriptions of music from an audio file. Provide an audio input and an instruction prompt, an...
Tag music audio with genre and instrument labels. Accepts an audio clip and returns a list of predicted tags such as gen...
Classify music approachability and engagement from an audio file or YouTube URL. Return two-class (low/high), three-clas...
Classify music styles from audio. Accepts a YouTube URL or audio file and predicts the top N styles among 400 Discogs st...
Transcribe piano audio into MIDI note events. Accepts a piano recording and outputs a MIDI file with polyphonic notes, o...
Analyze music structure from an audio file. Predict tempo (BPM), beats, downbeats, functional segment boundaries, and se...
Predict musical arousal and valence from an audio file or YouTube URL. Return continuous emotion scores (valence, arousa...
Classify music by genre, mood, and instrumentation from an audio file or YouTube URL. Return predicted tags and confiden...
Analyze music to extract song structure, tempo (BPM), and downbeats from an audio file. Return a JSON timeline of sectio...
Transcribe polyphonic music audio into MIDI. Accepts an audio file and returns a multitrack MIDI transcription with note...
Classify music styles from audio or a YouTube URL and return top-N genre predictions as JSON or a bar-chart visualizatio...
Estimate tempo (BPM) from an audio file or YouTube URL. Run Essentiaβs tempo algorithmsβdegara, multifeature, percival,...
Analyze music structure and split an input song into stems. Accepts an audio file and returns a structure analysis JSON...