Registry / Directory
Generative models
15 registered architectures
| Model / Developer | Architecture | Category / License | Description |
|---|---|---|---|
ACE Studio Timedomain | AI Vocal Synthesis Engine | voice_conversion Commercial Software | Specialized AI singing vocal engine with pitch, breath, and tension curve controls. |
ACE-Step 1.5 ACE-Step Open Source | DiT (Diffusion Transformer) Decoder | end_to_end Open Weights (MIT) | Open-source complete song generation model supporting local weights. |
AIVA AIVA Technologies | Symbolic Music Theory Transformer & RL | symbolic_midi Proprietary / Commercial | AI composition assistant exporting multi-track polyphonic MIDI and orchestral scores. |
Diff-SVC Open Source Community | Denoising Diffusion Probabilistic Models (DDPM) | voice_conversion Open Weights | Diffusion singing voice conversion engine for high-accuracy vocal reproduction. |
ElevenLabs Voice ElevenLabs | Proprietary Neural Synthesis | voice_conversion Proprietary / Commercial API | Generative speech-to-speech and text-to-vocal synthesis platform. |
Google Magenta / Music Transformer Google Research | Self-Attention LSTM & Transformer | symbolic_midi Open Source (Apache 2.0) | Research framework for symbolic melody, drum groove, and expressive accompaniment. |
MusicGen (AudioCraft) Meta AI | Autoregressive EnCodec Transformer | Uncategorized Open Weights (CC-BY-NC 4.0) | Open-source controllable music generation model developed by Meta FAIR. |
MusicGen Large (AudioCraft) Meta AI | Autoregressive EnCodec Transformer | end_to_end Open Weights (CC-BY-NC 4.0) | Open-source controllable music generation model by Meta FAIR. |
Retrieval-based Voice Conversion v2 RVC Community | VITS-based Voice Conversion | voice_conversion Open Weights (MIT) | Neural voice conversion trained on target vocal stems using index retrieval. |
SOUNDRAW Soundraw Inc. | Hybrid Algorithmic & Neural Synthesizer | hybrid_workflow Proprietary / Commercial | Customizable, tempo-synced AI composition platform with granular stem control. |
Stable Audio 2.0 Stability AI | Latent Diffusion Architecture | end_to_end Proprietary / Commercial API | Full-length 44.1kHz stereo track synthesis and audio-to-audio latent diffusion. |
Suno v3.5 Suno AI | Transformer-based Diffusion | end_to_end Proprietary / Commercial API | Text-to-music generation model producing full arrangements and vocals. |
Suno v4 Suno AI | High-Fidelity Audio Diffusion Transformer | end_to_end Proprietary / Commercial API | Generates full-spectrum stereo compositions with natural vocal timbre. |
Synthesizer V AI Dreamtonics | DNN-based Singing Voice Synthesis | voice_conversion Commercial Software | Deep neural network singing synthesizer with natural pitch transitions and voice databases. |
Udio v1.5 Udio | High-Fidelity Diffusion Model | end_to_end Proprietary / Commercial API | Prompt-driven composition with surgical inpainting and stem separation. |