FunASR
Verified · 6 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Create and track AI music videos and audio-reactive visuals from songs.
claude mcp add --transport http compel https://compeller.ai/api/mcp
Hosted service that turns songs into AI music videos and audio-reactive visuals, exposed as 20 MCP tools covering discovery, generation, render tracking, and signed webhooks. The agent-facing documentation is unusually good — agents.json manifest, OpenAPI spec, honest long-running-job guidance — and discovery tools work without auth. Caveats: the application is closed source (the repo says so plainly), generation is paid, and the self-serve signup flow is designed so your agent can register an account with your email mid-conversation — know that before connecting.
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