FunASR
Verified · 27 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Self-hosted MCP server for speech: ASR transcription, TTS synthesis, and file staging tools.
claude mcp add talkies -- docker run -i --rm docker.io/psyb0t/talkies:v0.17.0
Talkies is a self-hosted speech server that bundles transcription, text-to-speech, and file staging into one MCP toolset. It is for users building local or controlled audio workflows who want one service to cover basic speech I/O. The self-hosted focus is useful, but the small footprint and OCI-only packaging suggest an early-stage project that may require more operational comfort than mainstream alternatives.
Transcribe local audio with FunASR and SenseVoice using private, on-device inference.
Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.
Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
Let any LLM watch a video locally — and search everything it has ever watched.
The Figma MCP server brings Figma design context directly into your AI workflow.
Natural voice conversations for AI assistants - STT/TTS via MCP