FunASR
Verified · 17 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Text to speech in any MCP client. Six voices, watermarked, free key of 100,000 chars.
claude mcp add gandr-mcp -- uvx gandr-mcp
A text-to-speech MCP server aimed at users who want quick voice generation inside an MCP client without setting up a separate audio stack. The free, watermarked tier makes the positioning clear, but the lack of visible adoption signals suggests an early-stage or niche project rather than a broadly proven option.
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 actually watch a video: scene-aware keyframes plus a timestamped transcript, local.
The Figma MCP server brings Figma design context directly into your AI workflow.
Natural voice conversations for AI assistants - STT/TTS via MCP