"Speech & Transcription" matching MCP servers:

MCP server for personal knowledge management providing AI-powered tools for semantic search, audio transcription, image generation, and PPT creation.

An MCP server that gives Claude direct access to your reMarkable tablet's notebooks, enabling document search, PDF rendering, handwriting transcription, and diagram conversion, all locally without API keys.

MCP server for extracting links from text dumps, checking duplicates, extracting YouTube transcripts (with fallbacks including speech-to-text), and preparing workspace-ready page payloads for your note-taking or saving tools. It does not write to your workspace; it hands off prepared content to your existing tools.

An MCP server that lets Claude read live transcripts and notes from Alt, a real-time lecture/meeting transcription app, while a recording is in progress, pulling only new lines each time.

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.

Provides MCP tools for interacting with esa, enabling read and write of posts, context management, auditing, administration, optional transcription, and GitHub integration.

Records your calls on your own computer, transcribes them on the machine, and lets an agent start, follow, question and annotate a call while it runs. No meeting bot, no account and no cloud; the same core runs as a self-hosted transcription server.

Enables agents such as Claude Code, Cursor, and claude.ai to search and read received speech recordings and retrieve signed audio links, using an agent key or OAuth.

A self-hosted, Streamable HTTP MCP server that turns spoken end-of-day voice entries into a personal diary, extracting promises and to-dos with due dates from ordinary speech, merging near-duplicates, and prioritizing what matters most with explanations. It also lets users ask what's due, mark commitments complete by meaning, and receive pattern observations and reflections, using Amazon Bedrock for language understanding with an offline fallback.

Search, read, and create speech-to-text transcripts on-device with the Whisper Notes Mac app. The MCP server is built into the app (macOS, Apple Silicon) and serves over a local Unix socket — 100% offline, no open ports.

Enables MCP-capable AI assistants to run live interview or discovery calls by loading Markdown question lists, starting and stopping local transcription, tracking answered questions, adding follow-ups, and saving or reading call transcripts and results.

Enables memo, upload, and transcription workflows through MCP tools.

Local-first meeting capture and transcription for Claude Code. Records audio from meeting apps, transcribes locally with whisper.cpp, and produces structured notes via Claude.

Connects Codex, ChatGPT, and other MCP agents to a Cordis account, enabling search, reading, creation, editing, and organization of notes and collections, media management, transcription, comments, and link retrieval via authenticated HTTP or stdio transports.

Enables agents to retrieve Bilibili videos as timestamped Markdown notes, with optional local transcription when captions are unavailable.

Exposes local, fully offline transcription with speaker diarization, voice-based speaker relabeling, environment diagnostics, and read-only workspace search as MCP tools for clients such as Claude Code and Claude Desktop. All audio, text, and voice embeddings stay on the user's Apple Silicon Mac, with no accounts, API keys, or cloud calls.

Connects a user's messaging account to an MCP assistant for conversation search, local transcription, attachment analysis, group monitoring controls, and durable scheduled messages.

Lets Claude and other MCP clients manage an Anki collection through AnkiConnect: create decks, add notes, import TSV/CSV files, search, edit, move, rename and delete cards, generate text-to-speech pronunciation audio into note fields, and sync with AnkiWeb. Changes are guarded by preview-and-confirm tokens, automatic backups, dry runs, and read-only or delete-disabled modes.

Enables semantic search over personal markdown notes by indexing them into a vector database and exposing search, reindex, and status tools via MCP.