voicemode
Natural voice conversations for AI assistants - STT/TTS via MCP
Updated October 2026
The best media MCP servers in October 2026 are voicemode, FunASR, Remove AI Watermarks. voicemode is the most widely used; Ffmpeg Skill is the most actively updated; FFmpeg is a good pick if you need a hosted server that also works in ChatGPT.
Natural voice conversations for AI assistants - STT/TTS via MCP
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
Identify and remove AI watermarks and provenance metadata from your own images and video.
Trim, convert, resize, compress, and remix audio and video.
Agent Skill that gives coding agents (Claude Code, Cursor, Codex) a local video editor: 42 FFmpeg tools with a machine-readable contract, contract-derived MCP server, FFmpeg capability detection, probe-first / verify-last workflow. Cut, join, silence remo
Composable image and video generation tools, reusable visual skills, and optional creative workflows for MCP clients
Operate your Sapiens Sintéticos AI studio: generate image, article, voice, music and video.
MCP server that gives Claude Code the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via multiple backends
Generate images, video, and audio with Glif's media-generation agent
Live New York events, shows, classes, tours, markets, music, theater, comedy, art and nightlife
See every one in Media.
Only maintained, original projects are listed. They are ranked by GitHub stars, with recent activity shown next to each. The list updates daily. See how we list and rank.
ChatGPT needs a remote server with a URL. FFmpeg, Sapiens Sintéticos, Glif, SyncSo offer one.