FunASR
Verified · 15 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Fixes the names and jargon speech-to-text gets wrong before your agent acts on a dictated prompt.
claude mcp add lexicon -- npx -y @ashlr/[email protected]
Lexicon corrects names and domain jargon that speech-to-text systems often misrecognize before an agent acts on a dictated prompt. It is best for voice-driven agent workflows in jargon-heavy settings, with a focused use case and limited public maturity signals.
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.
Screen recording, meeting notes, and voice dictation - all with AI
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.