Model Tracker
AudioGen
AudioGen is an AI model made by Meta. Meta released it on 2 August 2023. It is generally available. It takes text and returns audio. Its weights are open.
In inglese
AudioGen is an AI model made by Meta. Meta released it on 2 August 2023. It is generally available. It takes text and returns audio. Its weights are open. Its licence is CC-BY-NC 4.0.
- Released
- 2 August 2023 — ai.meta.com, read 16 October 2026
- Status
- Generally available — github.com, read 16 October 2026
- Takes
- Text — ai.meta.com, read 16 October 2026
- Returns
- Audio — ai.meta.com, read 16 October 2026
- Open weights
- Yes — ai.meta.com, read 16 October 2026
- Licence
- CC-BY-NC 4.0 — github.com, read 16 October 2026
- Context window
- Not confirmed: The reviewed Meta model card and API documentation do not print a standard context-window size.
- Longest answer
- Not confirmed: The reviewed Meta pages do not print a standard maximum output-token limit.
- Knowledge cutoff
- Not confirmed: The reviewed Meta pages do not state a knowledge-cutoff date.
- API price, input
- Not confirmed: The reviewed Meta pages provide no standard API input-token price.
- API price, output
- Not confirmed: The reviewed Meta pages provide no standard API output-token price.
- Where
- Downloadable weights — github.com, read 16 October 2026
- Parameters
- 1,500,000,000 — github.com, read 16 October 2026
- Model card
- https://github.com/facebookresearch/audiocraft/blob/main/model_cards/AUDIOGEN_MODEL_CARD.md — github.com, read 16 October 2026
Questions
When was AudioGen released?
Meta released AudioGen on 2 August 2023.
Is AudioGen still available?
Yes: it is generally available, as Meta states it.
Are the weights of AudioGen open?
Yes: Meta publishes the weights of AudioGen for download.
What is the licence of AudioGen?
The licence of AudioGen is CC-BY-NC 4.0, as Meta names it.
What does AudioGen take and return?
AudioGen takes text and returns audio.
How many parameters does AudioGen have?
AudioGen has 1,500,000,000 parameters, as Meta publishes it.
More from Meta
- Audiobox
- Chameleon
- CM3leon
- Code Llama
- DINOv2
- DINOv3
- Emu
- Emu Edit
- Emu Video
- EnCodec
- I-JEPA
- ImageBind
- LLaMA
- Llama 2
- Llama 3
- Llama 3.1
- Llama 3.2
- Llama 3.3
- Llama 4 Maverick
- Llama 4 Scout
- M2M-100
- Make-A-Video
- Movie Gen
- Multi-Band Diffusion
Sources
- Open sourcing AudioCraft: Generative AI for audio made simple and available to all (read 16 October 2026)
- AudioGen Model Card (read 16 October 2026)
- AudioGen: Textually-guided audio generation (read 16 October 2026)