"MCP servers for reading and parsing PDF, Word, and PowerPoint documents" matching MCP servers:

MCP server providing 115 tools to control the Windy Word voice-to-text desktop app, enabling paste, hotkeys, transcription, recording, and many other operations.

A local stdio MCP server that enables validated access to official ElevenLabs APIs with cost controls, local media storage, and audio export for Godot.

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.

Enables MCP-compatible clients to detect and remove speech filler words using timestamp-aligned transcripts, and generate precise cut lists for video editing workflows.

Translate PDF, Word (DOCX), Excel (XLSX) and PowerPoint (PPTX) files, images, subtitles and text. Turn audio and video into transcripts or translated subtitles. Preserve layout where supported. Requires an Equalang API key and credits.

Transcribes YouTube videos or audio files to Markdown, plain-text, and Word documents.

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.

Enables agents to inspect local videos, audio recordings, and documents by producing storyboard grids, timestamped transcripts, page images, and page-aligned text, with tools for probing media, zooming into details, locating terms, and reading subtitles. It works only with local absolute paths and does not download content or call an LLM.

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.

Pay-per-call x402 APIs for AI agents: DeFi token safety (honeypot/tax simulation, A-F grade), EVM chain data, web access (markdown/screenshot/PDF), speech-to-text. USDC on Base, no account, no API key

MCP server that scores dialogue transcripts for bridging quality, offering per-speaker indicator scores with evidence and tools for parsing, comparing, and analyzing conversations.

Enables MCP clients to transcribe local audio files or public audio URLs into plain text, JSON with word timestamps, or SRT/VTT subtitles, with options to save output to a file.

An MCP server that enables transcribing local audio files and Telegram voice messages using OpenAI's Whisper via local inference or cloud API. It supports multiple audio formats, automatic language detection, and optional word-level timestamps for AI-powered audio analysis.

Enables AI assistants to transcribe audio and video from URLs or local files with high accuracy, speaker diarization, 119 languages, and word-level timestamps, while also supporting transcription management and caption export in SRT, WebVTT, or plain text.

Lets MCP clients such as Claude list, read, search and compare transcripts of Apple Voice Memos on macOS, keeping word-level confidence marks so uncertain words stay visibly flagged. Adds speaker separation, optional local voiceprint recognition, and independent second-reader comparisons that highlight where two engines disagreed.

Enables Claude to read WhatsApp Desktop chats on a Mac, including messages, images, documents, and locally transcribed audio, through a local MCP server. Everything runs on the Mac with read-only access and no messages sent.

MCP server for the AssemblyAI API, providing tools for transcription, subtitles, speaker turns, word search, and LeMUR-based queries.

Enables reading, searching, transcribing, and sending WhatsApp messages through uazapi, with audio returned as transcribed text and media saved as local files for AI agent use.

Provides live meeting context to an AI assistant during Google Meet or Zoom calls, enabling real-time transcript reading, decision tracking, and actionable advice in a side panel.

A Node.js server that enables AI assistants to interact with Bouyomi-chan's text-to-speech functionality through Model Context Protocol (MCP), allowing for voice reading of text with adjustable parameters.

Enables users to extract transcripts from Douyin videos, parse video metadata, retrieve download links, and transcribe audio files, using HTTP parsing with Chrome/Edge fallback and SiliconFlow cloud ASR by default.

A stdio MCP server that enables long-form audio transcription through the NAVER Cloud CLOVA Speech API, accepting local files, trusted HTTPS URLs, or Object Storage keys with optional speaker diarization. It supports synchronous results and billable asynchronous jobs, letting clients check job status and retrieve transcripts with speaker labels and word timings alongside an offline health tool.

Know what your cloud agents did without reading logs. Heard MCP lets Claude, ChatGPT, Devin, Copilot and other cloud agents brief you out loud on your Mac, by name: what they got done, what's blocking them, or the decision they need. "Scout finished: the CI fix is merged." Answer out loud and the agent picks up your reply and keeps going. Hosted, OAuth sign-in, nothing to install.

Enables assistants to search meetings, transcripts and dictations, gather decisions and action items by person and deadline, locate who said what and when, and transcribe audio or video from links or files. Sign-in is via OAuth account access, with reading free and transcription charged per minute.

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.

Read-only MCP server for Telegram that enables reading messages and transcribing voice, audio, and video notes via the Telegram API for use with Codex and Claude Code.

Enables Claude to run a structured learning program by selecting topics, delivering lectures to a local site, reading and grading answers, tracking progress, and closing completed topics. It also serves a localhost website for viewing the curriculum and progress.

Enables AI agents to run SearXNG-powered metasearch across multiple engines and categories, with optional vector-based semantic re-ranking of results and Tavily-compatible responses. It also converts many document and media formats—including PDF, Office files, Outlook messages, and audio or YouTube recordings—into text.

MCP server for parsing Douyin video links, downloading watermark-free videos, and extracting speech transcripts using AI speech recognition.

Enables LLM agents to process local videos into timestamped, citable text documents and then query them through tools for listing videos, retrieving transcripts, and fetching specific segments, all fully offline.