declare-lab/tango
Tango is a diffusion-based text-to-audio generation system that uses LLMs to guide the audio synthesis process.
Not currently ranked — collecting fresh signals.
star history
Tango is a family of diffusion models for text-to-audio generation. It leverages large language models to guide the diffusion process, enabling generation of audio from textual descriptions. The project includes multiple model versions (Tango, Tango2) and associated datasets like Audio-Alpaca. It provides model weights on HuggingFace and demo applications for generating sound effects and audio from text prompts.
Frequently asked
- What is declare-lab/tango?
- Tango is a diffusion-based text-to-audio generation system that uses LLMs to guide the audio synthesis process.
- Is tango open source?
- Yes — declare-lab/tango is an open-source project tracked on heatdrop.
- What language is tango written in?
- declare-lab/tango is primarily written in Python.
- How popular is tango?
- declare-lab/tango has 1.2k stars on GitHub.
- Where can I find tango?
- declare-lab/tango is on GitHub at https://github.com/declare-lab/tango.