Home › Design & Media › loudkit
loudkit
Local text-to-speech from an on-device model: 28 voices in 10 languages, plus voice profiles cloned with the loudkit CLI. Tools list_voices, synthesize (base64 WAV, FLAC, MP3 or Opus) and describe; no cloud, no API key
Topics: Text-to-Speech
Connect
See the repository for installation instructions: https://github.com/loudreader/loudkit
Related servers
voicemode
Natural voice conversations for AI assistants - STT/TTS via MCP
kokoro-tts-mcp
MCP Server that uses the open weight Kokoro TTS models to convert text-to-speech. Can convert text to MP3 on a local driver or auto-upload…
claude-code-tts
MCP server plugin for Claude Code that converts text to speech using OpenAI's TTS API. Features 6 voices, worker pool architecture,…
daisys-mcp
Generate high-quality text-to-speech and text-to-voice outputs using the [DAISYS](https://www.daisys.ai/) platform and make it able to…
mcp-transcribe
MCP-Transcribe server allows LLMs to interact with the text content of audio/video files
brainiall-mcp-server
AI-powered speech tools: pronunciation assessment with phoneme-level feedback, speech-to-text with language detection, and text-to-speech…
Listed in punkpeye/awesome-mcp-servers (MIT)