11 tagged transcription, measured the same way as everything else here.
Browse within: speech-to-text 5
MCP server Claude CodeCodexCursor +2
MCP server "delive" as configured in XimilalaXiang/DeLive. Runs <PATH_TO_DELIVE>/mcp/delive-mcp-server.js with node. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "augent" as configured in AugentDevs/augent. Launched with augent-mcp.
MCP server Claude CodeCodexCursor +2
MCP server "transcreveai" as configured in DeHor-Labs/transcreve-ai. Launched with bash ./scripts/transcreveai-mcp --transport stdio.
lucasliet/youtube-transcript-mcp
MCP server Claude CodeCodexCursor +2
MCP server for fetching YouTube transcripts. Runs locally from the youtube-transcript-mcp npm package.
MCP server Claude CodeCodexCursor
MCP server "talky-talky" as configured in shawnrushefsky/talky-talky. Runs locally from the /Users/shawnrushefsky/code/shawnrushefsky/talky-talky Python package.
abid-mahdi/whisper-telegram-mcp
MCP server Claude CodeCodexCursor
MCP server "whisper-telegram-mcp" as configured in abid-mahdi/whisper-telegram-mcp. Runs locally from the git+https://github.com/abid-mahdi/whisper-telegram-mcp.git Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor
MCP server "voice-memo-hub" as configured in jremick/voice-memo-hub. Runs locally from the voice-memo-hub Python package.
MCP server Claude CodeCodexCursor
MCP server for dTelecom real-time speech-to-text with x402 micropayments. Runs locally from the @dtelecom/stt-mcp npm package. Needs 1 environment variable to run.
danielrosehill/Gemini-Transcription-MCP
MCP server Claude CodeCodexCursor +2
MCP server for audio transcription using Gemini models via OpenRouter. Runs locally from the gemini-transcription-mcp npm package.
MCP server Claude CodeCodexCursor +2
MCP server "m4x" as configured in closeofbusiness/m4x. Runs locally from the m4x Python package.
Novia-RDI-Seafaring/transcriber
MCP server Claude CodeCodexCursor +2
Transcribe interviews and panel discussions, identify who said what via speaker-embedding clustering, and relabel speakers in an interactive web UI. Runs locally from the dialogue-transcriber Python package.