- Multi-instrument to MIDI
Turn songs or ensembles into multitrack MIDI to correct notes, organize parts and edit arrangements in a DAW. Available models include MuScriptor, YourMT3+, MIROS.
- Vocal, harmony and accompaniment processing
Separate lead vocals, harmonies and accompaniment, or extract dry vocals for covers, karaoke and vocal editing. Available models include Sony MIMO BS-RoFormer, BS-RoFormer Leap XE + Leap Instrumental, BS-Kar AVG.
- Music stem separation
Split songs into vocal and instrument tracks for listening, mixing or practice backing tracks. Available models include CrowdioSet / PaRIRset SCNet, BS-RoFormer, Huge-SCNet.
- Drum separation
Separate drum recordings into editable instrument stems with DrumSep, IDM or MSG-LD; compare supported drums and outputs, then preview and download WAV files. Available models include MDX23C DrumSep, IDM, MSG-LD.
- Audio denoising and dereverberation
Reduce noise, crowd sounds or reverb in recordings, compare with the original and download the processed audio. Available models include XLANCE-MSR, MelBand RoFormer, Crowd MelBand RoFormer.
- Custom stem extract / remove (RoFormer)
One extracted target stem or a mix with that target removed. Practice tracks, accompaniment, remixing, sampling, and targeted cleanup.
- Piano to MIDI
Turn piano recordings into editable MIDI for notation, practice and arranging. Available models include TransKun V2, Aria-AMT piano-medium-double-1.0, D3RM.
- RVC Voice Conversion and AI Song Covers
Upload clean vocals or a separated vocal stem, choose an RVC v2 voice model and adjust pitch shift and pitch extraction. Compare the converted voice with the original, then download it for mixing with accompaniment. Separate vocals from a full song first.
- Speech synthesis
Provide a clean voice reference and text for ZONOS2 speech generation. Select the text language, adjust settings and check pronunciation and pauses before downloading 44.1 kHz WAV audio for narration, voiceover drafts or multilingual voice tests.
- MIDI file tools
Repair garbled MIDI lyrics, track names and markers, or embed timestamped LRC lyrics in your browser. Choose an encoding, check the text and download the MIDI. Files stay on your device; existing notes, timing and controller events are preserved.
- AI song generation · Lyrics, style and model comparison
Describe the style and supply lyrics to create a song with vocals and accompaniment using each selected model. Configure each model · YuE2 · LeVo 2 Large · MiniMax Music 3 · HeartMuLa 3B. Previews use 192 kbps MP3. Downloads and ZIP archives retain the original WAV.
- Audio to sheet music
Choose excerpt scoring or full-song melody and chord transcription, then download the selected model’s score and timed annotations. Available models include SheetSage2, HookKern.
- Piano velocity refinement · Score-HPT
Upload piano audio and a time-aligned piano MIDI to estimate note velocities. Pitches, timing, tracks, tempo maps and pedal events are preserved. Notes are not added or aligned automatically. MIDI
- Prompted sound separation
Describe a sound or provide reference audio to extract it from a recording and download it. Available models include AudioSep-Hive, FlowSep-Hive, CLAPSep.
- Multi-singer and choir separation
Separate overlapping singers and choir parts, listen to each and select parts for further editing. Available models include Concat / FiLM, UNMIXX, Chorus Male/Female BS-RoFormer.
- Dialogue, music and effects separation
Separate film audio into dialogue, background music and effects for dubbing and post-production mixing. Available models include SFC-LoCoFormer, Bandit, TIGER DnR.
- Speaker separation
Separate two overlapping speakers. Prefer recordings with two consistent speakers; turn-taking groups, music and strong reverb can affect quality. WAV
- Saxophone separation
The specialist Demucs v3 checkpoint outputs saxophone and accompaniment stems; Mega 53 can render an A/B result for the same file. Available models include Demucs v3 Saxophone, Mega 53.
- Single-instrument to MIDI
Convert solo or isolated instrument recordings to MIDI, then edit pitches and timing. Available models include SwiftF0, Basic Pitch, GAPS.
- Piano Video to MIDI · V2N
For fixed top-view keyboard video. Supply all four keyboard corners for perspective correction; V2N predicts physical key release and note velocity, not pedal-extended audio offsets. MIDI
- Lyrics-guided vocal transcription
Requires the vocal audio plus lyrics, phonemes and a phoneme-to-word map. Exports note MIDI together with phoneme, word and vocal-technique timing; it is not an audio-only route. Available models include STARS.
- Piano MIDI to MusicXML (MIDI2ScoreTransformer)
Converts an existing piano performance MIDI file into an editable notated MusicXML score with MIDI2ScoreTransformer. Raw audio is not accepted. MusicXML
- Vocals to MIDI
Convert singing, humming or vocal stems to MIDI. Compare ROSVOT, GAME, SOME and VOCANO results before correcting the melody. Available models include ROSVOT, GAME, SOME.
- Beat, key and chord analysis
Analyze BPM, beats, key and chords with timestamps for arranging, practice and mixing. Available models include Beat This! final0 + OpenKeyScan3, ChordMini, Omnizart ChordV1.
- AI song covers from reference vocals, without training
Upload a song and a reference from one singer. Choose any of seven cover models without training, with harmony removal, dereverberation, MP3 previews and WAV downloads.
- Drums to MIDI
ADTOF Plus · ADTOF Direct · ADT_STR · MSG-LD. Full mixes go through the model’s drum-extraction pipeline first. Isolated drums go directly to transcription or drum-stem separation. Available models include MSG-LD, ADTOF, ADT_STR.
- Guitar tablature
Choose SynthTab Universal, GuitarSet, EGDB or IDMT for clean/acoustic and matched guitar domains, or GuitarProFX TabCNN for electric-guitar tones and effects. The models predict six-string fret positions; TelkNet exports note events, six-track MIDI and timestamped tablature. Available models include CRISP · TabCNN, SynthTab, Noise2Fret + SynthTab.
- BPM Alignment, Stems & DAW Export
Preserve original speed or choose a target BPM. Analyze beats, key and chords; optionally separate vocals and accompaniment. Export WAV, MIDI/CSV, song tags and verifiable analysis. WAV / MIDI / CSV / JSON
- RVC model training
Train a private RVC voice from your singing or speech recordings for song covers. Continue an existing model, compare previews from different epochs, and download the model and index.