"Speech & Transcription" matching MCP servers:

Enables continuous voice conversation with AI coding assistants by locally transcribing speech with Whisper and delivering utterances as text prompts.

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

Enables AI agents to present interactive code walkthroughs with voice narration, opening files, highlighting code, and showing inline explanations with synchronized text-to-speech.

Connects a text-only coding agent to an OpenAI-compatible vision model so it can analyze images, screenshots, and UI mockups. Provides tools for general image understanding, OCR and code transcription, error-screenshot diagnosis, technical diagram and chart interpretation, UI-to-code/spec generation, and expected-versus-actual UI comparison.

Extract invoices and contracts from text or Markdown into typed JSON with Mistral. Optional OCR supports PDFs and images when your account has access and quota. Six tools by default: documents, OCR, chat, vision, code completion and transcription. Additional API tools via explicit profiles. Runs over stdio or Streamable HTTP. Community-maintained; bring your own Mistral API key.

Enables AI assistants to inspect what NVDA reads and says, including focus, accessibility trees, document text, and speech history, and optionally to perform keyboard actions that NVDA announces as if the user pressed them.

Provides voice notifications using Grok's text-to-speech API to alert users when Claude Code completes tasks, with support for both local and remote server configurations.

Open-source registry of structured API specs for African providers: payments (Wave, Paycard, ...), SMS and WhatsApp (Africa's Talking, Infobip, ...), identity, delivery and speech. AI agents read the real endpoints, parameters and gotchas and write the integration. Each capability is marked verified (tested against the live API) or ready (written from the docs, not yet tested).

Enables driving a Claude Code session from a linked personal WhatsApp account or an official Cloud API business number, with bidirectional messaging, full media and voice transcription, per-chat personalities, and context recovery after restarts. Inbound traffic is gated by pairing codes, allowlists and per-group policies, and tool-permission requests can be approved or denied remotely with an emoji reaction.

Enables AI agents to inspect UI screen recordings as token-efficient image sheets with changed regions boxed, single-frame flicker flagged, and speech aligned to frames. Exposes watch_video and zoom_video tools so agents can pull dense keyframes across any time range or one sharp full-resolution frame, all processed locally.

Enables hands-free voice collaboration with a coding agent: you speak requirements aloud and hear only short, plain-language progress and completion summaries while the agent edits code, runs tests, and fixes bugs in the background. It also handles continuous speech recognition with automatic turn detection, barge-in interruption, and spoken approval prompts before risky operations.

A single STDIO MCP server that provides 48 tools for browser and Chrome DevTools automation, HTTP requests, SQL and MongoDB operations, GitBook, system intelligence, disk management, web search, local transcription, and Ollama delegation, plus runtime connection to external auth-free MCP servers.

Enables driving an AI coding session directly from WhatsApp over either a linked-device connection or the official Cloud API, with bidirectional messaging, media, polls, and local voice transcription. Access gating, per-group personalities, and emoji-based approval of tool requests keep strangers out and let users authorize or deny actions remotely.

Enables agents to rank model variants and hunt down API offers for a specific task, estimate real billed cost, audit n8n/Make automations for overpay, missing fallbacks and deprecated models, and plan or run evaluation and canary suites on the user's own examples. It also supports price comparison, custom reseller channels with measured per-call cost, and non-LLM capabilities such as web search and speech-to-text.

Serves a single set of typed, validated tool definitions to MCP clients over stdio, letting them perform real actions through one controlled executor. The same definitions power a speech-driven OpenAI tool-calling agent, so voice and MCP clients share identical, validated capabilities.

A desktop notifier for AI agents that floats on screen and alerts users with chimes and speech bubbles when an agent calls its notify tool.

Enables driving a Claude Code session from WhatsApp over a linked device or the official Cloud API, with bidirectional messaging, full media support, local voice-note transcription, per-group personalities, and context recovery after restarts. Access control gates every inbound message, and tool-use requests can be approved or denied remotely with an emoji reaction.

Integrates the Reachy Mini robot or its simulation with Claude Code to provide interactive physical feedback through emotions, speech, and celebratory animations. It features advanced capabilities like sentiment analysis, semantic problem search, and cross-project memory to enhance the developer experience.

Normalizes dictated text by correcting speech-to-text misrecognitions using a personal lexicon before agents see the prompt, and lets agents manage terms, learn corrections, and harvest vocabulary.

Enables driving a Claude Code session from WhatsApp through either a linked device or the official Cloud API, supporting bidirectional messaging, media, voice transcription, access control, and remote tool approval.

Enables driving a Claude Code session from a linked personal number or an official business API account, with bidirectional text and media messaging, local voice-note transcription, emoji-based remote approval of tool requests, and pairing-code allowlist access control. Also supports per-group personalities, scheduled cron tasks, and conversation context recovery after restarts.

Generates narrated video walkthroughs of git commits, staged/unstaged changes, or entire codebases with AI-powered analysis, syntax-highlighted code visualization, and text-to-speech narration.

Enables driving an AI coding session directly from WhatsApp chat — bidirectional text, media and voice-note messaging with local transcription, pairing-code/allowlist access control, per-group personalities, and tool-permission approval by emoji reaction. Connects either as a paired linked device or through Meta's official Cloud API, with no API keys or Docker required.

Enables natural voice interaction with Claude Code through speech-to-text, supporting wake word activation and multiple backends like Whisper and Google. It allows users to execute commands and control their coding environment hands-free via their microphone.

Connects an AI coding session to WhatsApp as a linked device or official Cloud API number, enabling bidirectional chat with media, voice-note transcription, @-mentions, and context recovery. Inbound messages are gated by pairing codes, allowlists and per-group policies, and tool permission requests can be approved or denied by emoji reaction from the chat.

Enables coding agents to speak aloud using text-to-speech functionality. Works with agents running inside devcontainers and provides configurable voice settings for creating chatty AI companions.