Keyword: transcription
- @otoji/core-darwin-arm64Released1m agoVersion0.1.34
音字 — realtime speech ⇄ text. Node/Bun bindings for the otoji Rust crate (SenseVoice ASR + multilingual polish + TTS).
- @otoji/core-darwin-x64Released1m agoVersion0.1.34
音字 — realtime speech ⇄ text. Node/Bun bindings for the otoji Rust crate (SenseVoice ASR + multilingual polish + TTS).
- @fuzeelogik/myfloReleased3d agoVersion1.5.1
myflo — local-first developer workbench. CLI + MCP server + Next.js dashboard. Forked from ruflo for the runtime substrate; flo CLI on top is ours.
- @transcribe-api/sdkReleased3h agoVersion0.1.10
Official JavaScript SDK for Transcribe API.
- react-native-deepgramReleased3d agoVersion2.1.1
React Native SDK for Deepgram's AI-powered speech-to-text, real-time transcription, and text intelligence APIs. Supports live audio streaming, file transcription, sentiment analysis, and topic detection for iOS and Android.
- minutes-mcpReleased3d agoVersion0.19.0
MCP server for minutes — conversation memory for AI assistants. Works with Claude Desktop, Mistral Vibe, Cursor, Windsurf, and any MCP client.
- @speakai/mcp-serverReleased2d agoVersion1.13.1
Official Speak AI MCP Server — capture meetings, search thousands of recordings, run async voice and video surveys, create clips, and automate workflows from your AI assistant.
- n8n-nodes-assemblyaiReleased5d agoVersion0.4.0
n8n node for AssemblyAI speech-to-text transcription models.
- @omniloy/sofia-sdkReleased2 weeks agoVersion1.0.6
Sofia SDK - AI-powered medical assistant web component for healthcare applications
- mirador-textoverlayReleased4d agoVersion1.0.4
Mirador 4 plugin to render a hidden or visible selectable text overlay
- video-context-mcp-serverReleased6d agoVersion1.3.1
A Model Context Protocol server that gives GitHub Copilot the ability to understand and analyze video content
- viber-channelReleased2d agoVersion0.7.1
Voice + text MCP channel between a Claude Code session and the Viber UI ( https://viber.dgypx.dev ). Push transcripts to Claude; send_message tool delivers text back to the UI.
- @picovoice/cheetah-react-nativeReleased5d agoVersion4.1.0
Picovoice Cheetah React Native binding
- @picovoice/cheetah-reactReleased5d agoVersion4.1.0
React hook for Cheetah Web SDK
- abjad-convertReleased13h agoVersion0.11.0
- @arvoretech/pi-elevenlabs-sttReleased5d agoVersion1.0.3
PI extension for push-to-talk speech-to-text using the ElevenLabs Scribe API
- @talkie/cliReleased20h agoVersion0.4.7
Access Talkie voice memos, dictations, captures, and workflows from the command line
- spoken-mcpReleased5d agoVersion0.2.1
MCP server for Spoken — fetch podcast transcripts as clean Markdown with real speaker names. Built for AI agents.
- @itsconvo/mcp-serverReleased6d agoVersion1.1.1
MCP server for Convo — AI meeting assistant. Access your meetings, transcripts, summaries, and action items from any AI assistant.
- @talkie/appReleased2 months agoVersion0.4.7
Install Talkie for macOS — voice-first productivity suite
- @videosailor/n8n-nodes-videosailorReleased16h agoVersion1.1.5
n8n community node to download, transcribe, trim, cut, resize, and subtitle videos via VideoSailor
- @effect-uai/inworldReleased2 weeks agoVersion0.8.0
Inworld speech-to-text and text-to-speech provider for @effect-uai/core.
- gilbert-mcpReleased5d agoVersion1.1.0
MCP server pour intégrer Gilbert (transcriptions et synthèses de réunions) dans Claude Desktop, Cursor, et tous les clients compatibles Model Context Protocol.
- @effect-uai/openaiReleased15h agoVersion0.9.0
OpenAI speech-to-text and text-to-speech provider for @effect-uai/core.