Local Qwen3-ASR transcription and realtime meeting capture on Apple Silicon.

Pi extension: transcribe audio with oMLX STT (Qwen3-ASR), validate the speech, and persist a JSON transcript sidecar beside each audio file.

Speech-to-text CLI: DashScope Qwen3-ASR + SpeakerKit diarization + dictionary correction. Bundles the transcribe skill as a self-contained npm package.

Voice input plugin (dual-face): mic button beside the composer send action, live recording bubble streaming PCM to a local Qwen3-ASR python service managed by the host, plus an ASR environment settings page (clone runtime/model repos, create venv, run ser

ASR client for vxbeamer, a self-hosted personal speech transcriber with real-time web interface.

asr2js and js2asr converter android string resource utils

React Native wrapper for sherpa-onnx TTS and STT capabilities

Real-time bilingual live caption server

Multi-engine ASR (Whisper + NVIDIA Parakeet) inference addon for qvac on the Bare runtime

SDK for Z AI Web Dev

剧本阶段统一 CLI：素材转 Script v4，并兼容 Script v3 的本地写作、精修、校验和发布。

MemberJunction Wrapper for HuggingFace speech-to-speech - self-hosted realtime (voice) driver (OpenAI-Realtime-compatible)

Qwen ASR Realtime WebSocket client with microphone recording

React Native binding of whisper.cpp

Multi-provider TTS + ASR adapter registry (OpenAI, Azure, GLM, Qwen, MiniMax, Doubao, ElevenLabs, VoxCPM, Lemonade / Whisper) — extracted from OpenMAIC.

qwen3 tokenizer for NodeJS/Browser

豆包输入法 ASR TypeScript 客户端

Pi extension for NVIDIA NIM — chat, vision (VLM), embeddings, and image generation

Speech recognition module for react native using Vosk library

Alibaba DashScope (ModelStudio) provider for oh my pi — Qwen3, GLM-5, MiniMax M2.5, Kimi K2.5 via OpenAI-compatible coding API