"Local and free services or resources" matching MCP servers:

Enables MCP clients to speak by running local voice models using Chatterbox Turbo TTS or Kokoro TTS, with support for voice cloning, paralinguistic tags, and multiple voices.

Enables coding agents to generate local GPU-accelerated narration audio from text, with tools for speech generation, job continuation, and model or voice queries.

A lightweight MCP server that provides offline text-to-speech via native OS speech engines. It allows AI assistants to speak task summaries instantly with no network calls.

A feature-rich MCP server for Discord, giving AI companions full presence in Discord communities — reading, responding, reacting, searching, and speaking.

Provides text-to-speech synthesis using Microsoft Edge's free TTS engine, supporting multiple voices, languages, and audio output options (base64 or file).

An MCP server that lets an AI assistant turn written text — or prose it writes itself — into narrated audiobooks with chapter-marked .m4b files, using local Kokoro voices entirely offline and free. It supports 54 voices across 9 languages, adjustable speed, voice blending, and chapter-level resumable rendering.

Enables assistants to open scripts in a centered, multilingual reader with direct paste, locale-aware word tracking, manual sentence navigation, pause/auto-scroll, and optional browser or OpenAI speech recognition.

Local Korean text-to-speech MCP server using a fine-tuned CosyVoice2 model, enabling voice synthesis directly from Claude or Codex with privacy and no API costs.

Enables local Vietnamese ecommerce copy preparation, source-grounded RAG retrieval, offline voice previews, correction-memory feedback, hook review, and fine-tuning dataset preparation without publishing posts or approving audio.

A server providing text-to-speech and speech-to-text functionalities using Windows' native speech services without external dependencies.

Local-first voice I/O for MCP clients, enabling hands-free dictation, spoken responses, and voice-based Q&A with coding agents.

Bridges a running GPT-SoVITS API into MCP clients for local speech synthesis with reference-audio emotion mapping, dialogue WAV stitching, voice and status inspection, and bounded audio resource retrieval over stdio or Streamable HTTP.

Enables agents to control a transparent, always-on-top desktop character window over a loopback-only local HTTP API — applying expressions, motions, parameters and gaze, speaking via TTS or uploaded audio with lip-sync, capturing screenshots, and switching models, window placement and visibility. Everything stays local, so no cloud account or manual token handling is required.

Exposes a local, hands-free voice room to any MCP client, letting agents read speaker-labelled conversation turns, wait for the next turn, list who is present, and speak aloud through local text-to-speech. Speech recognition, speaker identification and voice output all run on the user's own machine, so agents receive text with speaker names rather than audio.

Local spoken notifications for Codex with TTS and always-on-top overlay.

Enables cloning a voice from a local audio or video file and generating shareable audio-reactive waveform MP4 videos of spoken text, with customizable palettes, photos, and layouts, all through natural language from MCP-aware agents.

Enables coding agents to hold spoken conversations by exposing speech-to-text and text-to-speech tools over MCP, routing them to a local daemon that drives a Chrome window using on-device speech recognition and Piper synthesis. It supports listening, speaking, and reading files aloud within a Claude Code plugin or an MCP gateway.

A stdio MCP server that lets AI coding tools on a Mac speak text aloud through the local Speaklna text-to-speech app. It exposes four tools (speak, stop, status, voices) so agents can voice replies, halt playback, check state, and list available voices, but cannot import voices or change settings.

Voice interface for Claude Code enabling hands-free, conversational interaction entirely on-device for Apple Silicon Macs. It provides push-to-talk transcription and automatic spoken responses via local AI models.

Enables AI clients to convert text into spoken MP3 audio by calling a local voice gateway that renders it with the Eleven v4 model and delivers the result to either a local web playback list or a fixed Telegram chat. It also returns short clips as inline MCP audio content blocks for clients that support embedded playback.

Provides local text-to-speech output to PC speakers, Telegram voice messages, or MP3 files, and transcribes voice messages locally or via cloud. Includes tools for checking playback status, stopping audio, and replying to Telegram messages.

MCP server for casting audiobooks from a local filesystem library to Google Cast speakers, with playback control and local TTS support.

Enables text-to-speech and speech-to-text through MCP tools, using Groq's free hosted endpoints when configured and falling back to fully local keyless models otherwise. Also provides voice listing and provider health checks.

MCP server that enables AI agents to place real Telegram voice calls and speak a message aloud via TTS, with configurable repeats and call handling.

Enables coding agents to turn explanations of code, pull requests, or concepts into narrated slide walkthroughs voiced locally with Kokoro, returning a link that starts playing in about a second while the remaining slides are still being written. Slides are grounded in real files and git history, checked for errors, and exportable as static folders with captions.

An MCP server that converts short text summaries into spoken audio and plays them locally, designed for coding agents like Claude Code to announce task results.

Voice interface for Claude Code: you talk, the agent listens, codes, and talks back while it works. Live speech-to-text with turn-taking, Grok/xAI voices with per-subagent personas, and a real-time HUD dashboard.

Official Paxa Labs MCP server: Thai, English and Mandarin text-to-speech with local playback, voice design from a text description, speech-to-text with subtitles, translation into Thai, and document OCR with field extraction.

Enables progress-triggered text-to-speech in Cursor Agent, with speak and stop controls and voice matching the system UI language.

Sub-150ms clean Web-to-Markdown extraction, autonomous agent live web search, and neural speech synthesis for Claude Desktop, Cursor, and Windsurf.