#speech-recognition

Free, local voice dictation for Windows and Mac. Hold a key, speak, your words appear at the cursor. On-device Whisper, no cloud, no account, no telemetry.

🎙️ Talk to your coding agent. It talks back. Local-first voice I/O (MCP tools + Agent Skill) for Claude Code, Cursor and any MCP client.

Local-first AI dictation widget: faster-whisper speech-to-text, PyQt desktop UI, and system-wide voice input for terminals and coding agents. Supports Linux (X11/Wayland) and Windows.

Just blurt it. Record your screen, rant out loud, your coding agent files the bugs. 边用边吐槽，AI 帮你提单。 (Agent Skill for Claude Code / Codex)

REFRACT AI — turns resume + job description mismatches into evidence-backed signals, ranked priorities, and a personal improvement roadmap.

Native macOS floating voice assistant with a glass companion UI, powered by logged-in Codex or Claude CLI accounts.

小申陪伴：Windows 10/11 WPF 桌面宠物与本机多模态 AI Agent，支持语音、长期记忆、系统提醒和双架构单文件 EXE

桌面双语字幕工具：视频一键转双语 SRT/VTT；系统音频/麦克风实时字幕 + 置顶悬浮字幕条。macOS & Windows。| Desktop bilingual subtitle tool: video to bilingual SRT/VTT, realtime live captions from system audio & mic with always-on-top overlay. macOS & Windows. Qwen ASR + OpenAI-compatible translation, BYOK.

Belarusian speech recognition on the CPU: NVIDIA's Belarusian FastConformer through ONNX Runtime, an OpenAI- and whisper.cpp-compatible server, and a FLEURS benchmark

🎙 Open-source browser extension for voice-driven survey answering: reads questions aloud, you speak, say "next". BYOK LLM (OpenAI/Anthropic). Works on http pages. 问卷语音作答插件

Voice-controlled PowerPoint presentation assistant that lets you navigate presentations hands-free using natural voice commands.

A tool that transforms audio or video files into text transcripts and generates concise meeting minutes. Stay organized and efficient in your meetings, and get ready for Phase 2 where we'll be open for contributions to enable real-time meeting transcription!

Parley — voice-first portal to your own AI agent. Talk to it from your pocket. (formerly Sidekick)

灵音开源精简版 · Realtime voice AI engine with barge-in (WebRTC / VAD / STT / LLM / TTS)

Interactive voice-controlled storyteller for Raspberry Pi (ReSpeaker) or PC: OpenAI STT/LLM/TTS, RAG worlds, substory dramaturgy, moderation, de/en, web admin.

Cross-platform ASR strategy library: WhisperKit, Sherpa-ONNX (Parakeet TDT), NeMo, and faster-whisper behind one interface, with an OpenAI-compatible local transcription server

Quality-gated inference experiments and agent benchmarking for Starling.