Havuz

Native Android TTS app with on-device neural voices and emotion-aware prosody — sister project to marmalade-tts (CLI).

Assistente de voz para Linux que ouve você (Whisper local), pensa com o Claude Code e responde falando enquanto abre apps, mexe no volume e

Voice-first desktop assistant for Windows — talk to your PC and it works inside real apps, safely. By VORNEX.

Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.

100% offline transcription and TTS ecosystem built with Python, Whisper, and Piper.

Open-source voice agent OS. Rust runtime, AI-driven builder, sub second latency. Self-host everything.

The Open Source Voice Agent Platform - Build voice agents by connecting nodes in a canvas, deploy them to handle inbound and outbound phone

🐬 A pink qFlipper fork with LOTEI — a 100% local AI dolphin (Ollama) that chats, talks, watches your Flipper's screen, and one-click-install

Open-source alternative to ElevenLabs, HeyGen & Rask AI. Clone a voice, dub your video into another language and post it to YouTube Shorts,

Train voice styles for Supertone/supertonic-3 model.

Pure-Rust, memory-safe, CPU-only runtime for Qwen3-TTS zero-shot voice cloning: no Python, no ML framework, no GPU. Verified seam-by-seam ag

🌍 Real-time, offline screen translator for games & videos — OCR + NLLB-200 + subtitle overlay + neural voice dubbing that matches the speake

OpenAI Text-to-Speech API compatible server for Irodori-TTS

Offline neural TTS engine for Android. Registers system-wide, ships 186 voices via sherpa-onnx (Piper / Kokoro / Kitten / Matcha / ZipVoice

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline

🐮 牛来动画生成器 —— 输入一段小故事，一条命令产出还原电影《牛来》风格的抽象动画：无厘头台词、严格同步的字幕与配音、粗糙低模的直立牛。Three.js 程序化 3D 渲染 + DeepSeek 剧本生成 + TTS 配音 + FFmpeg 合成，不依赖视频大模型。AI vid

Tiny, fast Brazilian Portuguese text-to-speech (21M params)

Prepackaged medical pronunciation dictionary for voice AI TTS engines. 960+ drug names, clinical terms, anatomical terms, and medical acrony

Claude Code skill: turn any topic into a hand-drawn whiteboard explainer video with voice-over and captions

Narrated, 3Blue1Brown-style 4K math explainer videos built in Rust with franken_manim (native TeX, no LaTeX, no Python) and voiced by Franke

Open-source, voice-first AI mock interviewer. Upload your CV + a job description, practice out loud with an adaptive multilingual interviewe

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.

Fully local voice AI for iOS

OpenAI-compatible HTTP server for OmniVoice text-to-speech

Open-source Burmese AI recap workspace: find short videos, write Burmese recaps, add AI narration and captions, and export MP4. Laravel + Ne

KinoDraw: turn any script into a hand-drawn whiteboard explainer video, free and open source, on your own computer.

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

Voice I/O for LLM chat UIs: dictation, read-along and a voice-reactive aura, for any OpenAI-compatible speech engine.

Voice agents that speak your caller's language: listening, turn-taking, barge-in and the voice, in 29 languages. Open source.

Kesha listens and talks back: local speech to text and text to speech for agents and scripts, fastest on Apple Silicon.

开源本地版 Language Reactor + ELSA：把任意视频变成听力 / 跟读 / 发音训练 · Open-source local alternative — turn any video into listening, shadowing & pronunciati

An NVDA screen-reader synthesizer add-on that exposes Google's Chrome WASM text-to-speech voices to NVDA.

An explanation compiler for Claude Code: first-principles explanations in controlled prose, diagrams, interactive pages, or 3Blue1Brown-styl

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

Sard (سَرْد) — a desktop EPUB & PDF reader with first-class Arabic typography. Tauri 2 + Rust + React. Offline neural text-to-speech, spoile

Amalia Android Assistant

VoiceTut-TTS is an Egyptian-Arabic text-to-speech system fine-tuned from OmniVoice on ~380 hours of Egyptian podcast speech. It produces nat

Ultimate Streamer Voice Lab 2026: AI TTS, Soundboard & Voice Modulator Pro Toolkit

Full fine-tune Pocket TTS на русской речи. Синтез на CPU, клонирование голоса, управление ударениями и потоковое аудио.

Get 4.0 GPA without learning

Local text-to-speech: 28 voices, 10 languages, voice cloning, SDKs for Python, Swift, Go, Rust and TypeScript

Unofficial community companion for Windows: write letters and get replies from Linli (林离), with long-term memory, a daily world, QQ chat, vo

Self-hosted, OpenAI-compatible speech server: faster-whisper STT and Piper/Kokoro TTS. A local voice backend for Open WebUI, CLIs, and custo

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

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

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

A local browser reading app powered by MOSS-TTS-Nano with in-browser ONNX inference

Self-hosted AI voice agent for Asterisk. Streaming STT to LLM to TTS over AudioSocket, with barge-in and tool calling.

Reading companion for totally blind learners: the screen or a PDF read aloud in Arabic and English, offline first (NVDA add-on and a natural

AI video auto-dubbing plugin for coding agents — translate & dub videos into multiple languages via the Perso Dubbing API. Works with Claude