FunASR
Verified · 20 days agoTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
three.ws Audio
Verified · 32 days agoText-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents.
Install
claude mcp add audio-mcp -- npx -y @three-ws/[email protected]
Our take
An audio workflow server covering text-to-speech, speech-to-text, lipsync, and motion-capture clips for 3D or embodied agents. It is for developers building avatar, animation, or voice-driven agent experiences rather than ordinary transcription users. The feature set is ambitious, but current adoption signals are modest, so it reads as a specialized project still proving out reliability and depth.
Verification record
- 32 days ago
- 108
- 33 days ago
- no
- Apache-2.0
- 0.1.2
- 2026-07-20
More in media
browse all →Figma-Context-MCP
Verified · 25 days agoGive your coding agent access to your Figma data. Implement designs in any framework in one-shot.
openshorts
Verified · todayTurn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.
FFmpeg
Verified · 4 days agoTrim, convert, resize, compress, and remix audio and video.
Agent-Native Clips
Verified · 23 days agoScreen recording, meeting notes, and voice dictation - all with AI
claude-real-video
Verified · todayLet any LLM watch a video locally — and search everything it has ever watched.