AI Speech Solutions for Tasks such as ASR, Vocal Extraction, Accompaniment Extraction, Audio Denoising, and Enhancement, Support models such as paraformer, sensevoice, fireredasr, zipformer, moonshine, wenet, whisper, fsmn-vad, silero-vad, CT Transformer punc, Spleeter, Uvr5, etc, apply ONNX models in various scenarios.

• UpdatedFeb 14, 2026
• C#

基于 SenseVoice 的 Windows 本地语音转文字工具，支持 OpenAI 格式 API 润色，低延迟，高精度。

• UpdatedFeb 20, 2026
• Python

Tool for speech recognition using sensevoice-small

• UpdatedNov 11, 2025
• Rust

A Rust-based, SenseVoiceSmall

• UpdatedFeb 20, 2026
• Rust

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。

• UpdatedFeb 15, 2026
• Go

handy cli tool to convert your speech to clipboard text

• UpdatedJan 29, 2026
• Python

This repository provides a Docker image for SenseVoice

• UpdatedJan 18, 2025
• Python

Docker镜像自动构建并上传到阿里云

• UpdatedApr 21, 2025
• Dockerfile

⚡ Offline speech-to-text plugin for OpenClaw — 1s cold start, 228MB model, Chinese-optimized. Powered by SenseVoice + Rust + ONNX Runtime. 离线语音转文字插件，秒级响应，中文优化，支持中/英/日/韩/粤五语。

• UpdatedFeb 16, 2026
• Rust

🎙 Automated offline video transcription for macOS — FunASR + speaker diarization + language detection (zh/en/mixed). Zero cloud costs, 100% local.

• UpdatedFeb 13, 2026
• Python

Python pipeline to run SenseVoice ASR on Intel CPU/GPU/NPU thru ONNX Runtime + OpenVINO Execution Provider

• UpdatedDec 5, 2025
• Python

Offline Speech-to-Text for React Native using sherpa-onnx Supports Zipformer, Paraformer, NeMo CTC, Whisper & more.

• UpdatedJan 26, 2026
• C

🎤 Transform speech to text on Windows with fast, local AI processing. Enjoy seamless recording and automatic integration for effective communication.

• UpdatedFeb 20, 2026
• Python

语音识别

• UpdatedMar 31, 2025
• Go

Docker镜像自动构建并上传到阿里云

• UpdatedApr 21, 2025
• Dockerfile

ESP32 voice assistant with M5Stack Atom Echo + Echo Base. Push-to-talk with Opus streaming, SiliconFlow STT/TTS, and LLM agent integration. Built on ESP-IDF native framework.

• UpdatedFeb 16, 2026
• C++