Voice input for Fcitx5 — local and cloud ASR, LLM rewriting, cross-distro packages
-
Updated
Apr 19, 2026 - C++
Voice input for Fcitx5 — local and cloud ASR, LLM rewriting, cross-distro packages
Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)
妙语 - 智能语音输入,妙语亦可生花。
🎙️ VoxSherpa TTS Offline Neural Text-to-Speech Engine for Android ⚡ Sherpa-ONNX powered 🔊 Natural voice synthesis 📱 Fully offline processing 🚀 No cloud • No limits
Open-source offline voice dictation — a free alternative to Typeless. 100% local, zero internet, ideal for air-gapped & classified environments. SenseVoice + DirectML GPU, ~34MB, hotkey-driven. 纯离线语音输入,Typeless 免费平替,数据永不出设备,适合党政机关等涉密场景。
xiaozhi esp32的C#服务端,帮助你搭建属于自己的小智服务。Helps you build your own xiaozhi esp32 back-end service.
React Native TurboModule for Sherpa-ONNX offline on-device Speech Processing (STT/TTS/Diarization/VAD) completely offline on the device. Support for Android & iOS
Whisper.cpp with diarization
"it just vibes your audio into text bro" - 🐦⬛
Let’s start chatting with your Live2D or VRM girlfriend in iOS (Support Local LLM, API, Apple Intelligent)
Flutter app example with local speech recognition and voice command control using Sherpa-ONNX
[Deprecated] Go STT server. Successor: github.com/anatolykoptev/ox-whisper (Rust, OpenAI-compatible, WebSocket streaming).
Unity plugin for sherpa-onnx — offline TTS, ASR, and VAD with one-click setup
一个实时字幕工具,基于 sherpa-onnx 的 asr 模型完成实时字幕识别。A real-time subtitle tool that completes real-time subtitle recognition based on the asr model of sherpa-onnx.
Sona is a powerful, offline transcript editor built with Tauri, React, and Sherpa-onnx. It provides fast, accurate, and private speech-to-text capabilities directly on your local machine.
flet_sherpa_onnx an ASR/STT library for flet basing on sherpa-onnx
Offline-first AI voice input for macOS. 8 ASR models + 6 cloud providers, AI polish via 12 LLMs, 11-language translation, flash notes, AI organize, AI debug, correction feedback. 598 tests, fully private.
Offline Speech-to-Text for React Native using sherpa-onnx Supports Zipformer, Paraformer, NeMo CTC, Whisper & more.
On-device perception stack for Rust: OCR, CLIP, face recognition & streaming STT — one crate, many ONNX models, with lazy loading, 3-minute idle eviction, and an optional sidecar worker that exits on idle.
Add a description, image, and links to the sherpa-onnx topic page so that developers can more easily learn about it.
To associate your repository with the sherpa-onnx topic, visit your repo's landing page and select "manage topics."