MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
—
-
This is a model context protocol server for voice cloning using coqui.
-
mcp-voice-clonegithub.com/kevinten-ai/mcp-voice-cloneupdated this year
MCP server for voice cloning and advanced TTS via Fish Audio and ElevenLabs. Clone voices, generate speech, create sound effects.
MIT -
Clone your voice on Apple Silicon: local text-to-speech with voice cloning (VoxCPM2) and speech-to-text (Whisper) on MLX, as an MCP server for Claude. No cloud, no API keys.
MIT ★ 2 -
Open-Source Voice Cloning, Voice Design, Video Dubbing & Model Context Protocol (MCP) Server for Linux
MIT -
Japanese anime voice design and reference voice cloning with local CPU inference, A/B playback, and Gradio MCP
MIT -
Local MCP voice plugin for Codex / Claude Desktop / Cursor — cloned TTS via AuK-Flash on Apple Silicon, fully offline
MIT -
voicestudio-mcpgithub.com/aiworkmagic/voicestudioupdated this year
MCP server for Voice Studio — text-to-speech, voice cloning, voice design, transcription, and music generation as agent tools.
pypi MIT -
phantom-voices-mcpupdated this year
Claude MCP Server for PHANTOM VOICES — 10 free professional AI voice clones. Lets Claude recommend, search, and browse voices with platform-ready configs for 18 platforms.
npm MIT -
CHeema-Text-to-Voice-MCP-Servergithub.com/MuhammadTayyabIlyas/CHeema-Text-to-Voice-MCP-Serverupdated this year
Free, local text-to-speech and voice cloning MCP server for Claude Desktop, Claude Code, and n8n. No API keys, no cloud, no per-character billing.
NOASSERTION ★ 1 -
Clone your own voice once, then create dialogue in it with Gemini 3.8 Live and Flash TTS, from Claude (MCP), Python/CLI, ADK/Genkit agents, realtime web/phone apps, or a remote OAuth 2.1 server. Consent-based, with per-user isolation.
★ 1 -
muse-tts-embedgithub.com/falcoschaefer99-eng/muse-tts-embedupdated this year
Persistent audio player embedded in Claude's chat. 54 voices, voice cloning, play/pause/seek/download. Fully local.
NOASSERTION ★ 3 -
MCP server wrapper for VoiceStudio (debpalash): local voice cloning & TTS via OmniVoice on DGX Spark. ASMR DSP pipeline included.
AGPL-3.0 -
voxcpm-mcpgithub.com/coffeegrind123/voxcpm-mcpupdated this year
MCP server bridging VoxCPM2 multilingual TTS to any MCP client — voice design, cloning, and speech synthesis as agent tools
-
Command line and MCP server access to Murmur, offline text-to-speech and voice cloning for Mac
npm MIT -
Sovereign local-first AI voice studio. Neural speech synthesis, zero-shot voice cloning, zero-latency dictation, and MCP agent voice I/O. Built with Tauri & FastAPI.
AGPL-3.0 -
Turn Markdown scripts into multi-voice podcasts on your own PC: local voice cloning (F5-TTS, XTTS v2) or commercial cloud TTS (ElevenLabs, Azure, OpenAI). Desktop app, CLI and MCP server.
NOASSERTION ★ 1 -
higgs-audio-webgithub.com/neosun100/higgs-audio-webupdated this year
🎵 All-in-One Docker deployment for Higgs Audio v2 with Web UI, REST API & MCP support. Features: Expressive TTS, Zero-Shot Voice Cloning, Multi-Speaker Dialog, Text Profile Voice.
Apache-2.0 ★ 3 -
Official Gnani AI MCP server — Speech-to-Text, Text-to-Speech, and Voice Clone for Indian languages
pypi MIT -
Self-hosted text-to-speech for Supertonic 3: 31 languages, voice cloning, OpenAI-compatible API, realtime WebSocket, MCP server and a no-terminal web Studio.
MIT -
ha-addon-voiceboxgithub.com/ITSpecialist111/ha-addon-voiceboxupdated this year
Home Assistant add-on for Voicebox - local AI voice studio (TTS, voice cloning, transcription, MCP server). Includes a RAM preflight that refuses to start rather than trigger the OOM killer.
★ 1 -
Local GPU text-to-speech for AI agents via MCP - Chatterbox turbo/nano/multilingual, zero-shot voice cloning, resident worker with sentence batching, and a local web panel for worker control, model state, speak, replay and stop.
MIT ★ 2 -
Clone a voice on your own laptop, with the owner's permission, and let your AI agent talk in it. Checks every take before you hear it and watermarks everything. CLI + MCP server, no cloud.
MIT -
Local speech for Macs, Apple Silicon and Intel: text-to-speech with voice cloning and a studio voice, speech-to-text, system-wide dictation, and call recording with transcript, notes and speaker separation. Runs on-device with Metal. Daemon with an OpenAI-compatible HTTP API, a CLI and an MCP server.
Apache-2.0 ★ 1 -
🔌 Exposes Voice & Audio. TTS, voice cloning, audio generation, transcription. Integrates with Kokoro TTS and Whisper STT. (MEOK AI Labs)
pypi NOASSERTION ★ 1 -
Voiceover & captions MCP server for AI agents: turn a script into narration + SRT/VTT subtitles from Claude, Cursor and Codex. Voice cloning, emotion tags, transcription. Miragea voice engine.
pypi MIT -
muse-ttsgithub.com/falcoschaefer99-eng/muse-ttsupdated this year
Three TTS engines, 54 voices, voice cloning. Mac, Windows, Linux. Nothing phones home.
pypi Apache-2.0 ★ 1 -
elevenlabs-mcp-ttsgithub.com/kurojs/elevenlabs-mcp-ttsupdated this year
MCP server that gives AI assistants (OpenCode/Claude) a voice. ElevenLabs Text-to-Speech with 30+ AI voices, voice cloning, SSML, and automatic audio playback via PulseAudio — for any MCP host.
MIT -
Local OmniVoice TTS server with voice cloning, OpenAI-compatible API, FastMCP/MCP, Hermes Agent and Claude integration.
Apache-2.0 ★ 2 -
qwen3-tts-mcpgithub.com/Allen-han21/qwen3-tts-mcpupdated this year
MCP server for Qwen3 TTS - Voice synthesis, cloning, and design for Claude Code
-
Video editor for macOS that Claude drives through MCP: reels, screen tutorials, voice-over in your own cloned voice, captions and graphics, all local. By Arkad.
GPL-3.0 ★ 1 -
YouTube dubbing MCP server: AI dubbing for Claude, Cursor & Codex with one cloned voice per speaker, synced SRT and YouTube multi-language audio tracks.
oci MIT -
Production zero-shot voice cloning & studio TTS server in Rust. 646+ languages, cross-lingual synthesis, voice blending, biometric verification, broadcast DSP mastering, MCP protocol & embedded React 19 UI. Fast, private, fully self-hosted.
NOASSERTION ★ 3 -
A private voice studio for your computer: text to speech, voice design and voice cloning with open-source AI models (Qwen3-TTS). Built-in MCP server for AI agents.
Apache-2.0 -
agentic-cortexgithub.com/albert-ying/agentic-cortexupdated this year
A personal AI operating system built on OpenClaw/Claude Code, MCP servers, and structured markdown. Feedback RL, voice cloning, Screenpipe integration.
MIT ★ 24 -
elevenlabs-mcpgithub.com/neomorrison/elevenlabs-mcpupdated this year
ElevenLabs MCP server: 28 tools for text-to-speech, speech-to-text, voice cloning and design, sound effects, music, audio isolation and dubbing in Claude Code and any MCP client. Python, FastMCP.
MIT -
Free, offline ElevenLabs alternative. Clone and design voices, dub videos, transcribe, isolate vocals and make audiobooks, all on your own computer. Works with Claude Code, Codex and Cursor via CLI and MCP. MIT licensed.
MIT -
Open-source multi-speaker video dubbing: transcribe, find who speaks when, translate, and re-voice every speaker with their own cloned voice, with timing fit, ducked background, dubbed MP4, multi-language audio track and SRT/VTT. CLI + MCP server + Agent Skill, voiced by Miragea.
pypi MIT -
Native macOS Qwen3-TTS speech studio, voice cloning, dialogue, and local HTTP/MCP service. Swift and MLX; MIT licensed.
MIT ★ 1 -
supertone-mcpgithub.com/supertone-inc/supertone-mcpupdated this year
MCP server for the Supertone TTS API — a composable toolkit of voice synthesis, discovery, cloning, and usage tools across 31 languages
pypi MIT -
Production-grade ModelContextProtocol (MCP) server for the Smallest AI Waves platform. Exposes all Waves TTS and voice cloning features as MCP tools and resources. Ready for deployment.
MIT ★ 1 -
MCP server that brings ElevenLabs to Claude Code — text-to-speech, sound effects, music generation, voice cloning, speech-to-speech, transcription, and voice isolation. 8 tools for industry-leading AI audio. Supports Multilingual v2, v3, Turbo, Flash, and Scribe models.
MIT -
Free, open-source, local alternative to ElevenLabs and Suno. AI sound effects, music with lyrics, text-to-speech and voice cloning on your own GPU (Stable Audio, ACE-Step and more). No account, no credits, offline. Windows/macOS app, HTTP API and a 21-tool MCP server for Claude Code and Cursor.
NOASSERTION ★ 217 -
Self-hosted Docker speech API for OpenAI-compatible transcription and text-to-speech, streaming ASR, voice cloning, phoneme recognition, and MCP.
oci WTFPL ★ 7 -
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
npm MIT ★ 132 -
Official Soundverse MCP server: make AI music in Claude and AI agents. Song generation, vocals, stems, voice cloning, remix.
-
You take the helm, your AI crews the busywork. A lean desktop video editor with tag points, a karaoke narration booth, cloned-voice narration, synthesized SFX, Start Recipes, and a built-in MCP server. vidhelm.com
MIT ★ 3 -
MCP server for AI voiceover, voice cloning and SRT/VTT captions: any-length text-to-speech with exact durations, captions from local files, per-scene narration for Remotion. Claude, Cursor, Codex.
pypi MIT -
demo-directorgithub.com/jayadevrana/demo-directorupdated this year
MCP server that turns Claude into a product presenter: native macOS screen recording, human-glide cursor via Swift CGEvent, Chrome DevTools direction, spotlight highlights, and Voicebox voice-clone narration — finished narrated demo MP4 in one call.
NOASSERTION -
Podcast MCP server and AI podcast generator for Claude, Cursor and Codex: text to podcast with two cloned host voices, episode MP3, SRT transcript, chapters and RSS feed.
oci MIT -
A universal, cross-platform MCP server that gives any MCP client — Claude Desktop, the claude.ai web app (Connectors), Cursor, Cline / Continue in VS Code, or your own application — native access to the full Replicate catalog: image generation, video, music, speech, upscaling, segmentation, LLMs, voice cloning, 3D, lipsync — anything Replicate host
npm MIT ★ 4 -
patter-mcpgithub.com/PatterAI/patter-mcpupdated this year
MCP server for the Patter Voice AI SDK — make and receive phone calls from any MCP-compatible client (Claude Code, Cursor, ChatGPT, OpenClaw, Hermes Agent, Codex). Streamable HTTP transport, self-hosted via git clone + npm start.
MIT ★ 4 -
@tomosborne/second-brain-mcpgithub.com/degendoes/second-brain-mcpupdated this year
MCP server for Tom Osborne's Second Brain — talk to Tom's voice-cloned AI agent built on 100+ interview answers + 21,000 marketing articles + 15 years of operator memory, from inside Claude Desktop, Claude Code, Cursor, or any MCP-compatible client.
npm MIT -
Self-hosted AI media studio on a Google Colab L4 GPU: text-to-image, image editing, text-to-video with sound, music, text-to-speech, voice cloning, image-to-3D and Whisper transcription. ComfyUI + web UI + MCP server.
AGPL-3.0 ★ 2 -
tqd-voicegithub.com/abm-dungtq/tqd-voiceupdated this year
🎙️ Xưởng giọng nói tiếng Việt chạy 100% trên máy bạn — clone giọng từ 5 giây, riêng tư tuyệt đối. Local Vietnamese TTS studio (Web UI + REST + MCP).
Apache-2.0 -
声来 (ShengLai) — 云端 Key 驱动的语音工作台:一句话克隆音色、说话合成、素材补全、稳定翻唱;纯 Python 标准库零依赖,MCP 服务器 + 本地 Web 面板。
MIT -
Public Preview: Generate and play speech with Hezky česky. Choose from 190+ unique voices—including people, creatures, dragons, and robots—or create a personal voice from an authorized recording.
npm MIT -
mobvoi-mcpstale
Mobvoi MCP Server
pypi MIT License Copyright (c) 2025 Mobvoi Inc. Permission is hereby granted, free -
synclub-mcpupdated this year
SynClub MCP Server
pypi MIT -
allvoicelab-mcpstale
AllVoiceLab MCP Server
pypi MIT License Copyright (c) 2025 All Voice Lab P