Havuz

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

Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted

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

Unified native AI runtime for Java 17+, Java 22+ (Panama FFM), Android & C++. Run GGUF LLMs, Vision, Video, Whisper ASR, TTS & Embeddings in

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

Cortes verticais 9:16 pra gameplay — grátis, open source e 100% no seu PC. Sem cadastro, com a sua chave de IA.

Pixel-Pets: A local, open-source virtual pet ecosystem on M5Stack. 100% AI-authored C++ (Claude) by a 10yo maker. Includes Muffin (LLM), Vis

Your agent cannot listen to audio. harken fixes that — locally. MCP server + CLI, one 13 MB binary, fully offline: no Python, no ffmpeg, no

Open-source alternative to OpusClip, Descript & Submagic.Cut long videos into short clips for TikTok, Reels & YouTube Shorts, with captions

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

MIT-licensed macOS dictation — hold a hotkey, speak, release. A no-subscription alternative to Wispr Flow: bring your own API keys. On-devic

Dub any video into another language and keep it in sync — no drift. Single-file Python CLI · per-speaker voices · 4 TTS + 5 translators · fu

Press a key, speak, text lands at your cursor. Press another, get a spoken answer. Local-first, lightweight voice dictation and assistant fo

Open-source local meeting transcription for Discord and Google Meet with real speaker attribution.

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

Local-first AI assistant for Windows: voice (Whisper+Piper), webcam vision, FLUX image gen, image-to-3D, memory, 80+ tools. OpenAI-compatibl

Hackable voice AI assistant for Windows: wake it with your voice, bring your own LLM (Claude/Groq/Ollama/OpenAI/Gemini), and it actually doe

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

Local Home Assistant voice stack for RK3576 with NPU-accelerated Whisper and Piper through Wyoming, plus openWakeWord and RKLLM.

Turn Instagram reels into a searchable content research library. Save, transcribe, and ask AI what hooks, stories, and CTAs made them work.

A blazing-fast, offline push-to-talk voice assistant. Features real-time Whisper.net transcription, auto-typing under caret, smart VAD, and

Archived — continues as Sprigo: https://github.com/ozerozdas/sprigo

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

Media, Subtitles, Translation, all-in-one. One engine, three frontends: PyQt6 GUI, Textual TUI, plain CLI.

Open-source AI short-form video generator — turn a topic into a captioned YouTube Shorts / TikTok / Reels video with AI visuals (fal) or fre

Chrome extension that turns video subtitles and tab audio into real-time 3D Chinese Sign Language with local Whisper.

crawl4ai for video & audio — turn any YouTube video, podcast, or recording into clean timestamped markdown, or a verified TTS/STT training d

100% offline voice dictation for macOS, Windows & Linux — Whisper & Parakeet on-device, no cloud, open source.

Simpaudio — free offline text-to-speech (TTS) voice studio for Windows. 40+ realistic voices in 8 languages via Piper & Kokoro TTS. Voice bl

Speech and language toolkit for Obsidian

X/Twitter posts to Markdown and Douyin/Xiaohongshu video transcripts; local-first content collection with Obsidian and Feishu.

ThorOS - a voice-controlled, AI-first Linux distribution built on Debian 13. Say what you want; on-device AI plans it and permissioned agent

Published: 2026-10-18

Give your AI coding agent a voice: it speaks its decisions and questions, you answer by talking, and it can change your desktop. Local by de

Telegram bot that saves YouTube Shorts to Notion or Obsidian using AI extraction. Self-hosted, Docker, modular LLM backends.

RenderCaption - Offline AI Speech to Text & Subtitles Generator.

AI-powered voice-note device firmware (ESP32-S3): record, transcribe with Whisper, clean up notes with GPT, and auto-sync Markdown to GitHub

High-performance desktop studio for speech-to-text, subtitle translation, and video hardsubbing powered by whisper.cpp and FFmpeg. Fast, pri

Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings

Open-source, local-first screen recorder and timeline video editor for macOS and Windows.

Local-first AI video clipping tool that turns long-form recordings into short vertical clips with transcription, smart reframing, and captio

Local-first meeting recorder for Mac. Whisper on-device, your AI for summaries, MCP server for Claude Desktop.

Fcitx5 voice input addon — PulseAudio/PipeWire capture, Silero VAD, OpenAI-compatible & Volcengine Doubao streaming ASR, AsrSession architec

Speech-first inference runtime in Rust — TTS / ASR / speech-to-speech / VC / speaker ID / VAD. An ONNX Runtime alternative that loads GGUF &

本地 AI 驱动的实时对话翻译桌面应用（Real time dialogue translation desktop application driven by local AI）

Privacy-first dual-channel meeting transcription & AI summary for macOS — 100% local, powered by whisper.cpp and Ollama

中英混著講，落下的是乾淨的繁體中文。macOS 選單列語音輸入，whisper.cpp 全程在本機跑，kubectl、Terraform 這類術語內建修正。

Free, open-source AI dictation for Windows & macOS & Linux. Hold a hotkey, speak, and cleaned-up text appears in any app - BYOK or local mod

🗒️ A self-hosted personal fitness coach on Telegram, powered by the Claude Agent SDK with a Notion knowledge base and Google Calendar for sc

Premiere Pro UXP+CEP plugin that uses Whisper + LLMs to auto-edit talking-head videos. No cloud uploads.