"A server for detecting and analyzing intent" matching MCP servers:

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

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 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 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.

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.

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

An MCP server that enables AI agents to analyze videos locally by extracting transcripts, detecting scene changes, and returning key frames.

Provides various AI capabilities through DeepInfra's OpenAI-compatible API including image generation, text processing, embeddings, speech recognition, object detection, and classification tasks. Enables users to access multiple AI models for diverse tasks like generating images from prompts, transcribing audio, analyzing text sentiment, and performing computer vision operations.

MCP server for Chamade — a voice and chat gateway that lets your AI agent join meetings and DMs on Discord, Microsoft Teams, Google Meet, Telegram, SIP, Zoom, Nextcloud Talk, Slack, and WhatsApp.

Enables an AI to watch videos by sampling frames, reading on-screen subtitles via OCR, transcribing speech, and analyzing audio levels and spectra, all locally in pure Python.

Enables ChatGPT on the web to generate and play spoken audio through an embedded player, exposing a speak tool that renders text with selectable styles and scenes via configurable text-to-speech providers. It routes each request across ElevenLabs, Cartesia, Azure Speech, and DashScope in a configured failover order, picking providers by language and scenario.

Enables voice-driven family check-ins and safety escalation through five MCP tools over Streamable HTTP, recording check-ins, scheduling recurring reminders with grace windows, detecting missed check-ins, raising critical help alerts, and resolving them from a live dashboard. All reads and writes flow through these tools into a SQLite store, with safety rules ensuring explicit help requests override upbeat wording and never duplicate or downgrade alerts.

Enables Alexa+ to coordinate a household through 14 MCP tools: it tracks family members, auto-assigns and completes chores by workload, adds calendar events while reporting clashes, rotates pickup duty, manages a grocery list, and returns a spoken morning briefing with reasoning for every decision.

Enables AI agents to ring or text a user's actual iPhone, read a question or update aloud, and return the spoken answer back to the agent as text. Calls and messages land in a single titled thread per agent, with tools for polling results, waiting for replies, and labeling conversations.

Enables chat-driven audio analysis and enhancement using local Claude, including denoising, EQ, compression, and loudness normalization, with an A/B viewer for synchronized comparison.

Enables an AI agent to read and send real iMessages—including text, voice notes, stickers, links, images, and reactions—through a managed cloud phone line without needing a Mac.

Exposes stdio tools for analyzing code-switched multilingual utterances with PII redaction, running offline-first voice turns with local SQLite persistence, executing multilingual benchmarks, syncing store-and-forward outboxes, and exporting AI transparency cards. Runs with zero external runtime dependencies inside Claude Code, Cursor, Codex, or Antigravity.

A Model Context Protocol server implementation that enables AI assistants to interact with RetellAI's voice services for managing calls, agents, phone numbers, and voice options.

Enables fast, private voice control of smart-home devices and services through Alexa+ and a Tavus video assistant, with on-device speech recognition, PII redaction, intent routing, and voice-generated automations that are validated and hot-loaded.

A stdio MCP server that lets Claude Code sessions be driven directly from WhatsApp chats, with bidirectional messaging and media, voice-note transcription, pairing-code access control, per-group personalities, and emoji-reaction approval of tool requests. It supports both linked-device pairing for personal numbers and the official WhatsApp Cloud API for business DMs, and can also be run by other MCP clients on a poll-based basis.

Enables AI assistants to synthesize speech using a custom cloned voice through MiniMax TTS and present it in an inline audio player with waveform visualization and transcript controls.

Enables an assistant to turn any video ffmpeg can read into a text transcript by extracting the audio, splitting it on silence, and transcribing each piece on-device through utt. Exposes tools to start a transcription job with optional hints and timestamps, and to poll for a transcript that is still being worked on.

Enables AI agents to transcribe Instagram Reels into text by providing a tool that accepts a Reel URL and returns the speech transcript along with metadata such as author and duration.

Links your own WhatsApp account as a linked device on a computer you control and exposes it to Claude and ChatGPT over MCP, so assistants can search and read chat history, analyze attachments such as voice notes and PDFs, and send or manage messages only when explicitly asked. It runs self-hosted on macOS, Linux or Windows with an optional encrypted Cloudflare relay and a standby bridge for automatic, no-duplicate failover.

Enables shopkeepers to manage a credit ledger by voice in Hinglish—adding udhaar, recording payments, checking balances and top defaulters, drafting WhatsApp reminders, and mapping nicknames to customers.

Enables small dairy and crop farmers in India to talk to a voice-friendly farm ledger, with every number verified rather than guessed. It is a self-hosted MCP server over Streamable HTTP, planned to run on AWS Lambda with DynamoDB and Amazon Bedrock.

Self-hosted WhatsApp management over Model Context Protocol, exposing a streamable HTTP MCP endpoint with 30 tools for session/QR pairing, messaging, media storage, and optional on-CPU voice note transcription via whisper.cpp.

Enables voice assistants to screen voicemail transcripts for scam risk, returning a verdict with plain spoken reasons and suggested actions. Callers can then be blocked or reported through a two-step stage-and-approve flow that requires an explicit spoken confirmation.

MCP server for Douyin/TikTok short-video transcript and hook analysis, ranking content by save intent rather than likes and transcribing real speech to find reusable opening structures.

A self-hosted MCP server that connects AI clients to local media-generation backends like ComfyUI and Blender, and provides built-in utilities for video/audio analysis, editing, subtitles, speech, and scene detection via a persistent file cache.

Enables voice-driven control of a virtual Micro Duck through MCP tools for actions such as nodding, walking, turning, stopping, status checks, flash steps, and bear shakes, with animation preview and robotd/MuJoCo simulation backends.

Enables Poke to trigger outbound AI phone calls through Vapi telephony, using a stateless server with installer-owned credentials.

A local MCP server for Linux that records microphone audio and returns transcripts using local faster-whisper transcription.

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.

Enables students to ask by voice whether a specific topic is examinable on their exam — the digital SAT and PSAT, ACT, 24 AP courses, Alberta Diploma, and Singapore-Cambridge A-Level — returning the official syllabus's own wording, objective codes, and quoted exclusions rather than a guess. It also remembers which exams a student is taking and when, quizzes them on objectives, and reports weakest topics and days remaining for revision.

MCP server for GovTech's Transcribe speech-to-text service, enabling audio upload, batch transcription, summaries, minutes, sections, notes, and transcript Q&A.

Enables coding agents to open a review session on a web page, wait for spoken and drawn feedback, and receive actionable Markdown with transcripts, marked elements, selectors, and screenshots.

Enables a Claude Code session to send and receive WhatsApp messages through either a linked-device pairing or the official Cloud API, including media, local voice-note transcription, and @-mentions. It also gates inbound chats with pairing codes, allowlists and per-group policies, and lets users approve or deny tool requests with an emoji reaction.

A self-hostable MCP server for Roshan AI's Persian speech service, Harf, enabling transcription, forced alignment, real-time streaming, and speaker analysis through natural language.