"Document analysis tools for legal documents and evidence" matching MCP servers:

Provides local-first audio/video analysis by downloading media, transcribing it, and returning structured labels for topics, sentiment, sensitivity flags, and a publish/review/block gate.

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.

Provides local audio analysis tools for LLMs, enabling transcription, conversation dynamics, prosody analysis, and visual inspection without API keys.

Enables MCP clients to leverage the Intel Arrow Lake NPU for local speech transcription, screenshot OCR, private semantic search, and hardware diagnostics, all processed locally.

An MCP server enabling video processing via natural language: transcription with Whisper, segment cutting with FFmpeg, and file management.

Enables room agents to generate or edit images (published directly into the room's Docs rather than passed through the model's context) and transcribe audio attachments, using the deployment's media providers with the room itself acting as the credential.

An MCP server providing tools for speech-to-text, translation, language detection, question answering, and text-to-speech using Sarvam AI models, enabling multilingual voice agents.

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.

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.

Local MCP server that adds multimodal capabilities to text-only models like Codex/DeepSeek, offering tools for image description, audio transcription, video analysis, image/video generation, and speech synthesis.

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

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 real-time transcription and heuristic vocal stress analysis of live financial webcasts, providing an LLM with rolling transcripts and a stress score.

Enables Claude Code to leverage Chinese LLMs for multimodal tasks including image analysis, audio transcription, and deep synthesis via MCP protocol.

Official MCP server for the Vocametrix voice analysis API. Gives AI assistants direct access to clinical voice metrics (AVQI, DSI, jitter/shimmer, CPP), pronunciation assessment, speech transcription, prosody similarity, and AI-powered therapy planning. More than 40 endpoints for SLPs, voice researchers, and healthtech developers.

Enables AI agents to research Bilibili and YouTube videos through language, visual, or multimodal analysis, returning structured evidence with source-time ranges, availability states, and explicit analysis limits. Supports caption or audio-based transcription, sampled comments, and quality-controlled media windows.

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.

Enables local, upload-free analysis of publicly viewable videos through tools that pull metadata, chapter plans, platform subtitles or speech-to-text transcripts, sampled frames and contact sheets, 527-class sound event tags, and comment analysis. It downloads only the minimum necessary bytes, so users can inspect long videos section by section, job-poll lengthy runs, and check the local model/environment setup without sending media to any cloud service.

Extracts and formats Bilibili video content into structured text for LLM processing and analysis.

Provides multimedia understanding tools for LLM agents, enabling image, video, audio analysis and speech transcription via cloud-based MiMo V2.5 through OpenAI-compatible endpoints.

Enables agents on Windows to inspect video and audio evidence by returning adaptively selected frames, subtitles or optional local ASR transcriptions, timestamps, and processing status from local files or supported URLs.

Enables agents to clean up talk recordings by proposing cuts with evidence, importing user review decisions, and rendering frame-accurate ffmpeg output with verification.

A secure MCP server for Google Gemini AI, providing 39 tools for text, image, video, document, YouTube, research, and more. Runs locally via stdio with API key protection and no third-party services.

Enables users to convert text into high-quality audio by accessing the OpenAI Text-to-Speech API. It supports customizable model selection and voice options for synthesized speech generation via the MCP protocol.

MCP server and agent skills for Tough Tongue AI, enabling handling tough conversations through voice agents, scenario creation, and session analysis.

Provides multimodal understanding tools including OCR, image description, audio transcription, UI screenshot analysis, and screenshot comparison via async tools on a multimodal endpoint.

Remote MCP server wrapping the Bolna voice AI REST API, providing 11 tools (7 read, 4 write) for voice AI interactions.

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.