music-understanding AI Models

🤖 Model 🔊

zsxkib/audio-flamingo-3

Analyzes audio files with advanced understanding and step-by-step reasoning capabilities. Processes speech, music, and s...

🔊 • audio-to-text • music-understanding • speech-to-text • 58.6K runs

🤖 Model 🔊

aiviostudio/salmonn-2025

Processes audio files with text prompts to understand and analyze audio content, returning text-based responses about th...

🔊 • audio-to-text • audio-embedding • 77 runs

🤖 Model 🔊

aiviostudio/salmonn

Caption and analyze audio and music from an audio file using a text prompt. Provide free-form text responses to instruct...

🔊 • audio-to-text • music-understanding • 86 runs

🤖 Model 🔊

pengdaqian2020/music-label

Analyzes audio input to identify and classify music characteristics, returning text labels with configurable confidence...

🔊 • music-understanding • audio-embedding • 215 runs

🤖 Model 🔊

mtg/music-approachability-engagement

Analyzes audio files or YouTube URLs to classify music approachability and engagement levels. Uses EfficientNet embeddin...

🔊 • music-understanding • audio-embedding • 40.3K runs

🤖 Model 🔊

mtg/effnet-discogs

Classify music style and genre from audio. Accepts an audio file or YouTube link and predicts the top-N Discogs styles (...

🔊 • music-understanding • audio-classification • music-genre-classification • 321.0K runs

🤖 Model 🔊

bytedance/piano-transcription

Detects piano notes from audio recordings and transcribes them into MIDI format. Takes audio files as input and outputs...

🔊 • audio-to-audio • music-understanding • 4.7K runs

🤖 Model

sakemin/all-in-one-music-structure-analyzer

Analyzes music structure from audio input to predict tempo (BPM), beats, downbeats, functional segment boundaries, and s...

music-understanding • music-source-separation • 224.4K runs

🤖 Model

mtg/music-arousal-valence

Predict arousal and valence (music emotion) from an audio input. Accepts an audio file or YouTube URL and returns either...

music-understanding • music-emotion-recognition • 9.1K runs

🤖 Model 🔊

mtg/music-classifiers

Classify music by genre, mood, and instrumentation from an audio file or YouTube URL. Analyze audio using transfer-learn...

🔊 • music-understanding • audio-classification • 10.9K runs

🤖 Model 🔊

cwalo/all-in-one-music-structure-analysis

Analyze music to extract song structure, tempo (BPM), and downbeats, and optionally separate stems. Takes an audio file...

🔊 • music-understanding • music-source-separation • audio-embedding • 707 runs

🤖 Model 🔊

turian/multi-task-music-transcription

Transcribe music audio into MIDI. Accepts an audio file and outputs a MIDI transcription capturing pitches, onsets, and...

🔊 • music-transcription • audio-to-midi • music-understanding • 168 runs

🤖 Model 🔊

mtg/maest

Classify music into up to 400 styles from an audio file or YouTube link, returning the top-N predictions as a bar-chart...

🔊 • music-understanding • audio-classification • music-genre-classification • 9.4K runs

🤖 Model

mtg/essentia-bpm

Estimates the tempo (BPM) of audio files using Essentia's rhythm analysis algorithms. Accepts audio files or YouTube URL...

music-understanding • 35.2K runs

🤖 Model

erickluis00/all-in-one-audio

Analyzes music structure and separates audio into individual stems using Demucs and MDX-Net models. Takes an audio file...

music-source-separation • music-understanding • 104.6K runs

🤖 Model 🔊

riffgen/auto-tune

Auto-tune vocals from an input audio file, returning a pitch-corrected audio track and an optional pitch-correction visu...

🔊 • audio-to-audio • pitch-correction • 90 runs

🤖 Model 🔊

rhelsing/basic-pitch

Transcribes audio files to MIDI format using Spotify's Basic Pitch model. Takes an audio file as input and outputs a MID...

🔊 • audio-to-audio • music-understanding • 70.8K runs

🤖 Model 🔊

e7mac/omnizart

Transcribes audio files into MIDI format with multiple specialized modes including piano transcription, chord recognitio...

🔊 • audio-to-midi • music-understanding • music-transcription • 426 runs

🤖 Model 🔊

xavriley/sax_transcription

Transcribe saxophone solos from audio or YouTube links into MIDI and MusicXML sheet music. Accept an audio file or YouTu...

🔊 • music-transcription • music-understanding • audio-to-midi • 207 runs

🤖 Model 🔊

e7mac/beatnet

Analyzes music audio to detect beats and generate timing information. Takes mp3 or wav audio files as input and outputs...

🔊 • music-understanding • audio-to-audio • 878 runs