qwen3-asr 开源项目推荐（142 个）

buxuku /SmartSub

视频转字幕，字幕翻译，AI 配音与声音克朗，字幕字幕--免费开源的一站式桌面工具。基于 Whisper /FunASB等本地模型离线语音转文字，批量处理 + 全平台图形加速，运行Windows / macOS / Linux。免费开源桌面应用程序，可生成、翻译、配音和烧视频字幕-本地Whisper语音转文本、AI配音和语音克隆、离线、GOP加速。

meizhong986 /WhisperJAV

ASB/STT字幕生成器。使用Qwen 3-ASB、本地LLM、Whisper、TEN-VAR。适合JAV的噪音强劲

lucasjinreal /Crane

基于纯 Rust 的 LLM、VLM、VLA、TTS、OCR 推理引擎，由 Candle 和 Rust 驱动。可作为 llama.cpp 的替代方案，但更简单、更清晰。

crosswk /SayIt

Open-source voice typing for Windows and macOS — a Wispr Flow / Superwhisper alternative. Press a shortcut, speak, and AI-polished text lands at your cursor. Local models, your own API keys, or a self-hosted backend.

nyosegawa /speech.cpp

用于语音对话的语音合成、语音识别和语音活动检测，基于 ggml 的 C++ 实现：Qwen3-TTS、Irodori-TTS、Qwen3-ASR、ReazonSpeech、parakeet 和 Silero VAD，支持 Metal、Vulkan 和 CPU，附带兼容 OpenAI 的服务器和实时转写。

kukemc /bili-cli

为 AI Agent 设计的哔哩哔哩命令行工具：扫码登录、看视频、评论、私信、发动态、投稿，全部 JSON 输出

VladUZH /qwen-scribe

Private, local transcription and system-wide dictation for Apple Silicon.

zaigie /FunSpeech

开箱即用的本地私有化部署语音服务，快速搭建Qwen3ASR/FunASR与Qwen3TTS/CosyVoice后端

xinkyle /Voconly

本地优先 AI 语音输入工具 | Local-first AI voice typing tool. 支持 Whisper/SenseVoice/Parakeet/Qwen asr，离线可用，LLM 智能润色. Open-source speech-to-text with LLM post-processing, works offline.

victoryangzhijie /stt-server

Real-time speech-to-text WebSocket server with pluggable ASR backends, energy-based VAD, streaming partial results, and Prometheus observability.

sunerpy /voltip

Push-to-talk voice typing for Windows, macOS, Linux and Android. On-device or cloud speech recognition, AI polish with presets, a dictionary, rules and scenes, long recordings with subtitles; the phone works on its own or pairs end-to-end encrypted as the computer's microphone and keyboard.

Xingxun7777 /Aria

Windows 本地离线语音输入法：按一下反引号说话就出字，识别全程在本机（Qwen3-ASR，无显卡可用，NVIDIA GPU 可加速）；说错了喊一声「小助手」直接改；热词纠错、屏幕上下文、可选 AI 润色。Local offline voice typing for Windows.

LanceLRQ /qwen3-asr-service

Simple, Fast and Efficient Speech-to-Text API Service based on Qwen3-ASR. 简单快速高效的语音识别API服务

jaykwok /jav-trans

为 JAV 日语视频生成日文、中文或双语 SRT 字幕。支持本地音视频识别、时间轴对齐及 API 或本地模型翻译；网页界面操作，视频与音频留在本机。适用于 Windows + NVIDIA 显卡。

gabrimatic /local-whisper

Offline-first voice dictation, transcription, cleanup, and text-to-speech for macOS, iOS, and Android.

alan890104 /qwen3-asr-rs

纯锈推理引擎，适用于Qwen3-ASR语音识别模型（0.6B和1.7B），使用带有金属/CUDA加速的蜡烛

kaushiknishchay /ComfyUI-Qwen3-ASR

ComfyUI nodes for Qwen3-ASR (0.6B/1.7B) and ForcedAligner. Supports high-accuracy ASR and language identification for 52 languages/dialects, including 22 Chinese dialects and various English accents. Features word-level timestamps, long audio transcription, and VRAM-optimized inference.

iamwilliamli /LiveTranscriber

Public showcase and stable source-available foundation for the Live Transcriber App Store app.

frankzch /Saymore

Saymore：Windows 纯本地中文语音输入与口述整理工具。录音不上传云端，支持离线识别、书面润色、邮件整理、自定义术语和唤醒词；CPU 或 4GB 显存 GPU 均可运行。

christopherthompson81 /vernacula

ONNX speech pipeline library for ASR (diarization, VAD), and TTS