"A server for searching local files and summarizing articles" matching MCP servers:

Enables a local, cost-controlled voice assistant for macOS that routes requests between local and Claude models, provides draft-only email and calendar access via Thunderbird and Granola with a restricted allowlist, and supports meeting follow-ups.

Self-host a realtime voice-call companion for coding agents. Exposes an MCP endpoint that agents can poll as an alternate input stream.

Provides local vision and audio perception for MCP-compatible agents, enabling them to read images, transcribe text from visual media, analyze videos, and convert speech to text entirely on-device. It is privacy-focused with no cloud upload or API keys by default, using Ollama for inference.

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 AI agents to synthesize and play short summaries aloud while keeping full answers on screen, with queued speech and stop control using online natural voices or offline synthesis.

Private, local audio and video transcription for Claude: an MCP server that runs Whisper on your computer, on the GPU or CPU, with text, SRT subtitle, or JSON output. Works with Claude Desktop, Claude Code, and claude.ai.

Enables submitting audio via URL or Base64 for local Whisper transcription, then checking job status and results or deleting transcription jobs. It provides asynchronous job handling and SSRF-protected downloads/callbacks without cloud API calls.

Enables voice assistants to find nearby service providers, connect users to live video representatives for natural conversation, and handle appointment booking. It also returns confirmed bookings so the assistant can add them to its calendar.

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

Enables MCP-capable chat clients to synthesize speech from text, convert it with a local RVC voice model, and render the result in an inline audio player.

A FastMCP server that exposes a locally-hosted llama.cpp LLM as MCP tools, plus utilities for weather, news, web fetching, file I/O, and more. Enables MCP-compatible clients to use a local GGUF model for text generation without external APIs.

Enables AI agents to interact with a personal Telegram account via MCP, offering tools for reading and searching chats, summarizing unread messages, sending and editing messages, handling files and voice transcripts, and managing groups and channels, with read-only mode by default.

Transcribes audio/video files to text using NVIDIA's Parakeet TDT 0.6B V2 model, with optional timestamps; also retrieves model and system hardware info.

Enables AI clients to watch and hear videos from local files or YouTube, Vimeo, and Loom links by returning timestamped key frames, a transcript, a contact sheet, and a combined timeline, with all processing done locally.

Feedback ingestion for AI agents. Record your screen and talk; your agent does the rest — files the bugs, writes the spec, builds the backlog.

Turns a YouTube link into a readable, timestamped Markdown transcript by preferring existing subtitles and falling back to local Whisper transcription, with optional Traditional-to-Simplified Chinese conversion and Obsidian-friendly output.

Captions video and audio files on your computer with Cuecaps: animated word-by-word captions in 10 styles, exported as a burned-in MP4, a transparent MOV/WebM overlay for Premiere, Resolve or CapCut, or SRT/VTT subtitles. Rendering runs in local headless Chrome, so the video never uploads; captioning needs a Cuecaps Creator or Pro key.

MCP server for local speech-to-text using Whisper Large V3 (MLX), enabling audio transcription with text/timestamps/SRT output and LLM-based correction, all running offline on Apple Silicon.

Enables MCP clients such as Claude Code, Codex and Cursor to retrieve timestamped transcripts of public YouTube videos, either from cache, from native captions, or via asynchronous audio-generation jobs that are polled by job ID. It returns the source URL, selected language and millisecond-offset segments without summarizing the video itself.

MCP server for SpeechWeave transcription, enabling AI assistants to transcribe local files and URLs via wait-first or async tools.