Audio models
10
Models
7 organisations
40%
Open weights
4 open, 6 closed
0
Frontier
By Epoch's flag
860M
Largest traceable
MusicLM
2019–2026
Span
1 with a traceable size
Country
Records
10| Model | Organisation | Released | Parameters | Weights |
|---|---|---|---|---|
| Gemini Flash 3.1 TTS | Google DeepMind | 2026-04 | — | Closed |
| Suno v4 | Suno | 2024-11 | — | Closed |
| MultiBand Diffusion | Meta AI | 2023-11 | — | Open |
| AudioLM | Google Research | 2023-07 | 2B * | Closed |
| MusicGen | Meta AI | 2023-06 | 3B * | Open |
| AudioGen | Meta AI | 2023-03 | 1B * | Open |
| MusicLM | 2023-01 | 860M | Closed | |
| VALL-E | Microsoft | 2023-01 | 353M * | Closed |
| EnCodec | Meta AI | 2022-10 | — | Open |
| MuseNet | OpenAI | 2019-04 | 2B * | Closed |
An asterisk marks a parameter figure the source does not consider traceable to the people who built the model. That judgement is the source’s and it has false negatives: Kimi K3 is marked speculative at 2.8T while Moonshot’s own model card states the figure. Why that distinction carries the whole exhibit.
Counts are of models Epoch AI records as notable, not of every model released. The most recent month is always incomplete, because a model enters the dataset when it is reviewed rather than when it ships.
Epoch AI, 'Data on AI Models'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/data/ai-models-documentation' Used under CC BY 4.0.