Voice input for Fcitx5 — local and cloud ASR, LLM rewriting, cross-distro packages
-
Updated
Sep 7, 2026 - C++
#
offline-asr
Here are 32 public repositories matching this topic...
Windows 本地 AI 语音输入：Qwen3-ASR CPU/GPU 双运行形态、本地屏幕 OCR 上下文、热词纠错与可选 AI 润色。
python windows privacy ocr voice-commands chinese speech-to-text dictation screen-ocr voice-input voice-typing pyside6 llama-cpp local-ai offline-asr sherpa-onnx qwen3-asr
-
Updated
Sep 9, 2026 - Python
Real-time speech transcription and translation overlay for Windows. Powered by faster-whisper.
desktop-app python windows real-time translation subtitles speech-recognition opencc transcription whisper live-caption deep-translator customtkinter faster-whisper offline-asr
-
Updated
Jun 29, 2026 - Python
Lightweight real-time ASR powered by a Microsoft offline speech recognition model. CPU-only, supporting 10 languages, Windows, Linux, macOS, and C#, C++, Python SDKs. 基于微软离线语音识别模型的轻量级实时 ASR，纯 CPU 运行，支持 10 种语言及 Windows、Linux、macOS，提供 C#、C++ 和 Python SDK。
python windows macos linux csharp cross-platform cpp nuget pypi speech-recognition automatic-speech-recognition speech-to-text asr cpu-inference real-time-asr offline-asr multilingual-asr
-
Updated
Aug 1, 2026 - C#
中文 vosk-android-demo
-
Updated
Apr 24, 2024 - Java
Real-time English captions powered by offline April-ASR, with optional instant translation via Google Translate or DeepL. Designed for seamless live speech-to-text and multilingual translation, even without internet connectivity.
multilingual machine-translation speech-recognition speech-to-text speech-processing subtitle-generator offline-asr real-time-captioning real-time-translation
-
Updated
Sep 19, 2025 - Python
Offline speech-to-text for Russian, Kazakh, Kyrgyz & Uzbek on Apple Silicon — native MLX, quantized GigaAM, CLI and OpenAI-compatible local server.
macos speech-recognition russian speech-to-text transcription quantization asr kyrgyz mlx uzbek kazakh apple-silicon openai-api local-ai offline-asr gigaam russian-asr
-
Updated
Sep 8, 2026 - Python
基于 RK3588 的边缘语音监控原型，支持 ALSA 音频采集、离线 VAD/ASR、WebSocket 实时传输和浏览器可视化
-
Updated
Aug 21, 2026 - C++
按住右Ctrl说话，语音直达 Kimi Code 会话。本地识别不上云，说完零等待出字。
python windows accessibility speech-to-text asr kimi voice-input voice-typing offline-asr sherpa-onnx kimi-code
-
Updated
Aug 18, 2026 - Python
Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用
python machine-learning ai mcp speech-recognition vad speech-to-text whisper audio-processing speaker-diarization claude cpp20 rnnoise noise-suppression ai-agent real-time-transcription offline-asr subtitle-generation model-context-protocol mcp-server
-
Updated
May 19, 2026 - C++
Live speech-to-text streaming on Apple Silicon — Qwen3-ASR + Silero VAD + MLX
python macos speech-recognition server-sent-events speech-to-text transcription asr mlx voice-activity-detection live-captions on-device-ai apple-silicon silero-vad real-time-transcription local-ai offline-asr qwen3-asr streaming-transcription whisper-alternative
-
Updated
Mar 30, 2026 - Python
Offline free automatic speech recognition
python speech pytorch speech-recognition speech-to-text asr speech-recognition-api huggingface-transformers speech-recognition-apps speech-recognition-model speech-recognition-library offline-asr meta-ai hugging-sound
-
Updated
Jul 20, 2023 - Jupyter Notebook
Windows player for sentence-level language shadowing: bilingual subs, offline ASR, local progress
-
Updated
Aug 2, 2026 - Python
Privacy-first local WeChat chat viewer and complete exporter with offline Qwen3-ASR transcription.
-
Updated
Aug 16, 2026 - Go
Auditable Bilibili transcript workflow with local ASR, timestamps, resumable checkpoints, and low-risk correction review.
-
Updated
Aug 16, 2026 - Python
Private, offline push-to-talk AI voice input for Windows.
-
Updated
Jul 20, 2026 - C#
Offline CPU speech recognition for long-form audio and live streaming: deterministic three-model ensemble plus Nemotron-to-Parakeet cascade.
docker streaming cpp automatic-speech-recognition speech-to-text transcription nemo cpu-inference whisper-cpp offline-asr
-
Updated
Sep 2, 2026 - Python
OpenAI-compatible FunASR service for the Nota meeting recorder
windows docker self-hosted pytorch speech-recognition automatic-speech-recognition speech-to-text transcription asr speaker-diarization fastapi audio-transcription openai-api meeting-transcription paraformer local-ai offline-asr funasr sensevoice openai-compatible
-
Updated
Aug 26, 2026 - Python
Open-source mobile app for memorizing poetry using Spaced Repetition and Offline Speech Recognition (Sherpa ONNX). Built with Flutter.
poetry mobile-app spaced-repetition tts speech-recognition speech-to-text flutter offline-asr sherpa-onnx
-
Updated
Sep 4, 2026 - Dart
Offline speech recognition for robot Agents on NVIDIA Jetson. Fast, private, real-time voice input over DDS. Tested on Unitree G1 and Galbot G1.
robot robotics dds agents asr edge-ai jetson-orin offline-asr asr-services unitree-g1 sensevoice galbot-g1
-
Updated
Sep 7, 2026 - Python
Add this topic to your repo
To associate your repository with the offline-asr topic, visit your repo's landing page and select "manage topics."