transcribe_audio
8 registry entries were observed exposing a tool named transcribe_audio — none of them flagged as a privileged capability.
Spelled transcribe_audio, transcribe-audio in the wild — all one tool for the purposes of this page.
Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 8,470 of 26,658 scannable entries (32%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.
- @ffmpeg-micro/mcp-serververifiedMCP serverobserved · static extractionModel Context Protocol server for the FFmpeg Micro video transcoding API. Lets AI agents (Claude Desktop, Cursor, etc.) create, monitor, and
- @mindstone/mcp-server-elevenlabsverifiedMCP serverobserved · static extractionElevenLabs MCP server: TTS, music, sound effects, voices, and audio transcription
- com.ffmpeg-micro/mcp-serververifiedMCP serverobserved · static extractionMCP server for the FFmpeg Micro video transcoding API — create, monitor, download transcodes.
- io.github.rsmdt/multimodalverifiedMCP serverobserved · static extractionMulti-provider media generation — images, video, audio, and transcription via a unified interface
- MCP serverobserved · live tools/listOne key, 100+ models — chat with any LLM and generate video, images, speech. Free trial at 370.ai.
- MCP serverobserved · static extractionAI transcription from URLs or files. 119 languages, diarization, SRT/VTT/text export.
- MCP serverobserved · static extraction50+ pay-per-call APIs for AI agents — images, LLM, code, crypto, travel & more via x402
- MCP serverobserved · static extractionLocal audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.