Havuz

DSH 全双工语音插件：流式语音识别入草稿、语音合成按句朗读 + 实时字幕、开口即打断；本地识别免 API Key，可选唤醒词。 · Full-duplex voice plugin for DeepSeek Harness: streaming speech-to-text i

Parakeet Redux: Nvidia's 178MB AI Beats Whisper Running 113× Faster on CPU! - Lightweight, private CPU speech-to-text app powered by Moondre

A graph-native, local-first agent harness and Linux desktop shell: a voice-driven Executive Agent, a reviewed knowledge graph, per-Agent mem

听记 (Tingji) — 本地会议录音转写与纪要，FunASR + LLM，数据不出本机。Local meeting transcription & minutes, runs entirely offline.

Amalia Android Assistant

ZeusHammer - AI Super Agent with Local Brain, Voice Interaction & Three-Tier Memory

End-to-end subtitle translation workstation with cloud and local OpenVINO model support.

Fast, private, on-device dictation for Apple silicon Macs

A private AI companion web app for emotionally aware chat, voice notes, memories, shared activities, and gentle continuity.

Local, offline text-to-speech and voice cloning on audio.cpp — multi-voice narration, voice design, sound/music generation, and a real-time

Open, self-hosted runtime for real-time voice agents — a Rust recreation of ChatGPT's Advanced Voice Mode (GPT-Live), model-neutral

中文 AI 语音输入工具：按快捷键说话，在任意应用把口述变成去口头语、可分段和结构化的文字；支持用户词典、中文转英文和自选 ASR/LLM。

A macOS voice, screenshot, clipboard, and coding-agent workbench.

Streaming ASR, audio captioning and speech QA over a whisper-style encoder with pluggable LLM backends

Speak into any Android app — and have it write in another language. A dictation orb that appears only when a text field has focus, cleans up

Live on-device captions for macOS system audio. Core Audio process tap + NVIDIA Parakeet / Nemotron on the Apple Neural Engine. 16 languages

Free, open-source, local-first voice dictation for Windows and macOS. Offline speech-to-text with Whisper, Parakeet and GigaAM. Dictate into

Example macOS app and CLI to generate short clips, fully on device.

openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド

Generate degraded speech datasets for noise-robust ASR benchmarking

Free, open-source, fully-offline-by-default voice dictation for Linux (X11 & Wayland), macOS & Windows. Hold a key, speak, release — on-devi

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

Hands-free on-device voice loop for macOS: Apple SFSpeechRecognizer + cloned-voice TTS, continuous listening, zero cloud. Originally built t

Deploy streaming ASR + TTS on RK3576/RK3588 — 120ms TTS, 52-language ASR, one Docker command

A free, fully local, minimal-setup voice dictation app for macOS - built specifically for developers.

Live on-device transcription for Zoom and Google Meet calls on macOS. Knows the moment a question ends, then drafts an answer from your own

Free, offline AI pronunciation trainer for English & Spanish. Repeat a phrase, get an instant grade and the words to fix. Your voice never l

Real-time Windows system-audio translation captions for Chinese, Japanese, English, and Korean, with optional LLM revision.

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。

A voice-guided 3D ride through Singapore for young children, with tested speech matching and touch, keyboard, and grown-up fallbacks.

On-device streaming speech-to-text for macOS, built on Qwen3-ASR via MLX

ScribeCrate Live: self-hosted real-time transcription server powered by WhisperLive and faster-whisper. WebSocket transcription and speech-t

🦞 Headless real-time Python voice assistant powered by ElevenLabs, Gemini, Mem0, MCP tools, and local wake-word detection.

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

Community-maintained fork of FFmpegKit — Android SDK 35 ready, 16KB page support, LTS builds

CPU-first, eager-execution tensor/autograd runtime and LLM inference engine written in pure Zig

macOS 語音聽寫 App — MLX Whisper + Breeze-ASR-25，完全離線，Apple Silicon 最佳化

PASQA: Pitch-Accent-Focused Speech Quality Assessment Model Trained on Synthetic Speech with Accent Errors

Production-ready batch inference for Cohere’s Arabic/English ASR model, with optimized Silero VAD, multi-file GPU batching, subtitles, and o

Back to flow. Hold Fn, speak, and your words land at the cursor. Local-first dictation for macOS in 30+ languages.

Native Mac dictation in a 12 MB download. Free Local mode with Whisper + Parakeet, reproducible benchmarks, optional Cloud. MIT-licensed cli

On-device live transcription and translation CLI for macOS 26+ on Apple Silicon

Real-time speech transcription and translation overlay for Windows. Powered by faster-whisper.

🎯 AirControl - 隔空手势+语音控制系统 | Gesture + Voice Control System for Windows

Open-source JARVIS-class desktop AI. Zen mode orb, computer control, plugin marketplace, custom tools, local RAG, knowledge graph, voice per

Free, offline Whisper transcription for Windows, macOS and Linux. Turn audio and video into SRT, VTT, DOCX, PDF and more, with speaker label

QwenCleo-ASR is the currently State-Of-The-Art (SOTA) open-source model for Egyptian Arabic & code-switching speech recognition Built on Qwe

🎤 开源免费的 AI 语音输入工具 — 基于FunASR，本地处理，为中文而生 | Free & open-source voice input tool with local FunASR

Taiwanese Hokkien (Taigi) speech-to-text transcriber - MediaTek Breeze-ASR-26 with faster-whisper, tuned for RTX 3050 4GB low-VRAM GPUs. Gra