FunASR
Verified · todayTranscribe local audio with FunASR and SenseVoice using private, on-device inference.
Cue — video answers with timestamp-level proof. Scenes and frames stay off until asked.
claude mcp add cue -- npx -y @sylphx/[email protected]
Cue focuses on video question answering with timestamp-level evidence, exposing scenes and frames on demand. It is useful for users analyzing video archives or media evidence, though the narrow scope and very low download count make it feel experimental.
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.
Clip long videos into short clips with covers and captions. Local CLI and MCP.
Screen recording, meeting notes, and voice dictation - all with AI
Identify and remove AI watermarks and provenance metadata from your own images and video.
Turn long videos into viral vertical shorts and publish them to TikTok, Instagram and YouTube.