📡 MCP Radar

hassanxs/fatima-voice-studio

Voiceovers and voice cloning on your own Windows PC: Qwen3-TTS via llama.cpp, batches, voice library, OpenAI-compatible API and MCP server

⭐ 4 stars
⑂ 2 forks
Python
momentum ▲ 12.0
created 2026-10-07
on radar since 2026-10-11
star trend 3 → 4 since 2026-10-11
View on GitHub ↗

About fatima-voice-studio

Voiceovers and voice cloning on your own Windows PC: paste a script (or fifty), pick a voice from your library, and get each one back as WAV and MP3 at YouTube loudness, with SRT subtitles, in its own named, renamable folder. It runs Qwen3-TTS locally through the official llama.cpp engine: no cloud, no account, no per-minute cost, and the voice model is free for commercial use. It also works as an OpenAI-compatible speech API and as an MCP server for AI agents (Claude Code, Codex, Antigravity, Hermes…).

On a laptop RTX 5060 (8 GB) it speaks about 2.2× faster than real time: a 10-minute voiceover takes about 5 minutes, subtitles included. It also runs on AMD and Intel graphics cards (Vulkan) and, more slowly, on the CPU.

Hear it: English sample (18 s) · Spanish sample (17 s). Both made in the app on a laptop RTX 5060, with found voices (voices the model invented, nobody's real voice), levelled to −16 LUFS.

Get FatimaVoiceStudio-Setup-.exe from the latest release and run it. It installs for your Windows user only (no admin prompt) and is small, because the engine and models aren't bundled: the app downloads the ones that suit your PC on its Setup page, which opens by itself the first time (about 2.9 GB in all on an NVIDIA PC: engine 580 MB, voice model 2.3 GB, subtitles model 190 MB).

The installer isn't code-signed yet, so Windows SmartScreen may say "Windows protected your PC". Choose More info → Run anyway. Each release lists the installer's SHA-256, and the installer is built by GitHub Actions from the tagged source.

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/hassanxs--fatima-voice-studio.html)

Related MCP servers

2akouwu/reverify

Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is

⭐ 927Python
zhuyansen/new-term-radar

Daily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.

⭐ 893Python
yzg1226/mcd-party-officer

🍟 麦当劳门店派对成团调度 Skill — 把派对从「策划」推进到「办得成」:成团概率雷达 / 包场vs拼团 / 择日黄历 / 儿童营养指数 / 招募卡与邀请函

⭐ 234Python
fellowgeek/mcp-memory

An OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.

⭐ 188Python
hirotomasato/yowes

Generate realistic teacher documents (ID cards, licenses, letters) for 13 countries via MCP.

⭐ 174Python
hujjun/mcd-saver-strategist

麦当劳省钱点餐助手(麦门精算师)|麦当劳优惠券组合优化 Skill:拉取麦当劳菜单与全部可用优惠券,算出最省的点餐组合,巨无霸套餐 ¥47 → ¥21.9(省 53%)。McDonalds MCP(麦当劳 MCP)coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品

⭐ 161Python

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.