yan5xu/ququ
Open-source desktop voice dictation workflow tool with local FunASR models and configurable LLM text processing.
Not currently ranked — collecting fresh signals.
star history
蛐蛐 (QuQu) is an open-source, free alternative to Wispr Flow for Chinese voice input. It runs FunASR speech recognition models locally for privacy-preserving transcription, and integrates configurable LLMs to remove filler words, auto-correct errors, and format output into emails, code snippets, or other structures. Supports macOS, Windows, and Linux with local processing to avoid cloud dependency.
Frequently asked
- What is yan5xu/ququ?
- Open-source desktop voice dictation workflow tool with local FunASR models and configurable LLM text processing.
- Is ququ open source?
- Yes — yan5xu/ququ is an open-source project tracked on heatdrop.
- What language is ququ written in?
- yan5xu/ququ is primarily written in JavaScript.
- How popular is ququ?
- yan5xu/ququ has 2.2k stars on GitHub.
- Where can I find ququ?
- yan5xu/ququ is on GitHub at https://github.com/yan5xu/ququ.