fcitx-vinput
Voice input addon for Fcitx5 with local sherpa-onnx ASR and LLM postprocess
fcitx5-vinput is a voice input addon for the Fcitx5 input method framework. It performs on-device speech recognition with offline sherpa-onnx models and can optionally route the recognized text through any OpenAI-compatible LLM endpoint for error correction, formatting and translation. Cloud ASR providers can also be added at runtime through a downloadable registry. The package ships the fcitx5 addon, a background daemon, a command line client and a Qt6 graphical configuration tool. The prebuilt sherpa-onnx and ONNX Runtime shared libraries are bundled privately.
homepage ↗ github: xifan2333/fcitx5-vinput
Available in
| Overlay | Newest | Ebuilds | Last activity | |
|---|---|---|---|---|
| gentoo-zh GitHub ↗ | 2.3.5 | 1 | 14 h | details › |
Versions & arches
Use flags of 2.3.5
- systemd Enable use of systemd-specific libraries and features like socket activation or session tracking