Model Tracker
Audiobox
Audiobox is an AI model made by Meta. It takes text, audio and returns audio. Its licence is research-only license.
- Released
- Not confirmed: two readings disagree: 2023-12-11 and 2023-11
- Status
- Not confirmed: Meta describes Audiobox as a research model released to selected researchers, and says the demo is no longer available as of February 2026. Its pages do not assign one of the register’s status labels or say that the model itself is no longer served.
- Takes
- Text, Audio — ai.meta.com, read 16 October 2026
- Returns
- Audio — ai.meta.com, read 16 October 2026
- Open weights
- Not confirmed: The official pages do not state whether Audiobox weights are open or downloadable.
- Licence
- research-only license — ai.meta.com, read 16 October 2026
- Context window
- Not confirmed: The official pages do not print a context-window value.
- Longest answer
- Not confirmed: The official pages do not print a standard maximum-output limit.
- Knowledge cutoff
- Not confirmed: The official pages do not state a knowledge-cutoff date.
- API price, input
- Not confirmed: The official pages provide no standard-tier API input price.
- API price, output
- Not confirmed: The official pages provide no standard-tier API output price.
- Where
- Not confirmed: Meta says the demo is no longer available as of February 2026 and describes release to selected researchers, but the official pages do not establish a current availability category from the register’s list.
- Parameters
- Not confirmed: The official pages do not publish a parameter count.
- Model card
- Not confirmed: The official pages link to a research paper, but do not provide a model card.
Questions
What is the licence of Audiobox?
The licence of Audiobox is research-only license, as Meta names it.
What does Audiobox take and return?
Audiobox takes text, audio and returns audio.
More from Meta
- AudioGen
- 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
- Audiobox: Generating audio from voice and natural language prompts (read 16 October 2026)
- Audiobox: Unified Audio Generation with Natural Language Prompts (read 16 October 2026)