ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV

Windows 本地 AI 语音输入法 — 离线语音识别，屏幕感知上下文，热词纠错，语音指令操作选区。Local AI voice typing for Windows — offline speech-to-text with screen-aware context.

Pure-Rust inference engine for Qwen3-ASR speech recognition models (0.6B & 1.7B) using candle with Metal/CUDA acceleration

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.

MLX Local Serving (MLS) - Unified ASR, TTS, and Translation on Apple Silicon

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

Qwen3-ASR Serverless Worker for RunPod

A high-performance C/C++ inference server for Qwen3-ASR , optimized for CPU-only real-time streaming speech recognition.

A simple speech recognition API service based on Qwen3-ASR. 基于Qwen3-ASR的一个简单的本地语音识别API服务

Easily convert speech to timed SRT subtitles and translated captions (Colab-ready)

A free, open source, and extensible speech-to-text application that works completely offline.

🎙️ Implement fast, dependency-free C inference for Qwen3-ASR speech-to-text models with efficient streaming on modest hardware.

On-device voice transcription, grammar correction, and text-to-speech for macOS. Runs on MLX.

Live speech-to-text streaming on Apple Silicon — Qwen3-ASR + Silero VAD + MLX

A native TTS/ASR server macOS app run in local, OpenAI-compatible voice API gateway. Ready for OpenClaw. Supported models — Kokoro TTS, Kitten TTS, Qwen3 TTS, MiMo v2 TTS, FireRedASR v2, Qwen3 ASR, and more (local or cloud).

Local voice-to-text for macOS and iOS. Multilingual (EN/ZH/JP) with Traditional Chinese output. Runs Qwen3-ASR on Apple Silicon via MLX. No cloud, no subscription.

[en]Lora-finetuning for Qwen3-ASR[zh]对千问3ASR的Lora微调

Local Linux voice typing based on Qwen3-ASR | 本地 Linux 语音输入，基于 Qwen3-ASR 模型

A fully offline speech-to-text app for macOS

Fully on-device macOS voice input app. After recording is complete, AI performs batch analysis of the context, enabling transcription with higher accuracy than real-time methods. Since it converts text after understanding the meaning of entire sentences, misconversions of homonyms are significantly reduced.