Havuz

A lightweight macOS menu bar companion that reads copied conversation text and AI responses from Codex, Kimi Work, Deepseek, QianWen, and ot

🚀 Zero-backend, 100% client-side local AI assistant starter template. Powered by WebGPU and Google LiteRT-LM (Gemma 4). Offline-first PWA wi

Wtonec：微信 / QQ / 小红书 / 抖音文字转语音、语音包、语音播报、克隆音色、表情包。上百款音色，所有功能免费，无需充值。Android LSPosed/Xposed 模块。

Fast singing-voice acoustic model: harmonic + noise excitation refined into a mel by a 1-step rectified flow (bundled NHVSing vocoder). Mult

DeepSeek Harness 语音朗读插件：沉浸式听朗读，用豆包 TTS 自然音色读 AI 回复（BYOK · 点读/暂停/继续）

Clonación de voz y texto a voz 100% local con Qwen3-TTS y llama.cpp. Funciona en CPU y GPU, 10 idiomas, interfaz web en español.

Cross-platform, fully-offline Vietnamese/English text-to-speech desktop workstation powered by VieNeu-TTS v3 Turbo (ONNX/CUDA, Voice Cloning

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

559 K パラメータの日本語 TTS を ESP32-S3 で実時間合成。漢字かな交じり文の形態素解析・アクセント推定まで端末内で走る（M5Stack CoreS3 実機で確認）。推論は依存ゼロの C99、ブラウザ demo あり。arXiv:2608.21378 sanoTT

樱读 · Sakura Read — 二次元风格的 Android 小说阅读器（Flutter）｜TXT/EPUB 阅读 + 阅读3.0书源 + 看板娘桌宠

Self-hosted voice for coding agents. Talk from any browser or a Telegram call, interrupt mid-sentence, clone any voice, and hand real work t

Text-to-speech for Zotero 10: more voices, word and sentence highlighting at once in your own colors, speed and navigation shortcuts, one vo

免费开源 Windows Edge TTS GUI：文字转 MP3、实时进度、网络诊断、中英文界面与白夜主题 | 官网 edgettsgui.ainav.site | Free open-source Windows Edge TTS GUI.

Persistent agents for Claude Code as a plugin, not a harness. Memory, personality, messaging across WhatsApp, Telegram, and Discord, plus a

Self-hosted voice gateway in Go that speaks the OpenAI Realtime (GA) WebSocket protocol and runs a cascaded ASR → LLM → TTS pipeline behind

24/7 AI-DJ radio in Go. Persistent ffmpeg→Icecast with live ducking, LLM banter, BYOK, editable skills. ~50MB RAM.

🎬 AI全自动短视频引擎 — 基于 Pixelle-Video，新增 HappyHorse (DashScope) 云端文生视频。无需GPU，输入主题一键生成完整视频。Apache 2.0。

Rust-first, local-first multi-agent runtime with a desktop HUD, policy-gated tools, voice, and worktree-isolated coding agents.

The One Dashboard every Voice Agent needs

Single-container self-hostable Readest fork — SQLite + local FS, no Supabase, no paywall. Community: https://nodebyte.cn

启创墨域Chevoink——一款面向长篇小说的 AI 创作平台：可恢复任务、版本化正文、来源可追溯的研究与质量检查的创作平台。React / TypeScript / PostgreSQL，附阅读与社区。

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

Real-time voice translator for video calls. Speak your language on Google Meet, Zoom, or any call app — the other person hears translated sp

OpenAI-compatible speech serving in Rust: streaming TTS and full-duplex voice over GPT-Live. 128 concurrent PersonaPlex sessions on one GPU.

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

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

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

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

🔊 Hear how developers actually pronounce kubectl, nginx, GIF & 1,900+ tech terms. Sourced dictionary + CLI + VS Code + GitHub Action + MCP +

AI 驱动的短视频制作系统。给它一个想法，它帮你写稿、配音、做画面、出成片。9 阶段 DAG 管线 + 自进化评分，支持每日自动执行。基于 Claude Code + HyperFrames。

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

Small, fast, free: an open recipe for a sub-100M TTS. Code, data, weights. The PoC trained to a working model in a few hours on one RTX 3090

Free, open-source text-to-speech reader for Windows 11/10 in the system tray: natural Microsoft online voices, offline HD voices (Piper & Ko

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

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

Sano – Tạo sách nói bằng AI từ file Word. Chạy trên máy bạn, miễn phí, mã nguồn mở.

🐮 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

Local TTS voice mode for Claude Code with word highlighting and no cloud APIs.

The Humanness Index: the open benchmark for how human voice AI sounds, built by Vapi. Blind same-voice battles, pure-vote Elo, with a real-h

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

A directory of benchmarks for the components and complete systems used to build voice agents.

HomeAssitant Notifier Hub

Autonomous YouTube AI agent: LLM script, TTS voice, stock clips, FFmpeg editing, AI thumbnail, auto-upload — 100% free, Telegram-controlled.

A self-hosted app that turns RSS feeds into conversational podcasts for commutes. 将 RSS 转成对话式播客，让通勤成为轻松获取信息的时刻。

Paper Algorithm - An AI-agent skill set that turns one sentence into a finished voiceover video. | 纸上算法 · 一句话到成片的口播视频生产线：选题、写稿、出片、发布计划。

王陆语料库雅思听力单词听写练习工具（内置发音 + 乱序测试）| IELTS listening vocabulary dictation practice with built-in TTS pronunciation and shuffled tests

SpeakCrate: self-hosted text-to-speech API powered by Kokoro. OpenAI-compatible speech endpoint, 50+ voices across 9 languages, streamed aud

A unified Model Context Protocol server for MiniMax CLI (mmx)

[IJCAI2026] Official code for paper "Cross Domain Test Time Scaling: Scale Knowledge and Reasoning on Cross Domains"

把小米 MiMo 全模态能力(对话/图像/视频/TTS/声音克隆)封装成 stdio MCP Server,Claude Code 与 Codex 可直接调用