transcribeMCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@transcribeMCPtranscribe the audio file meeting.mp3 and get a summary"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
transcribeMCP
MCP server for GovTech's Transcribe speech-to-text service. Lets an MCP client (Claude Code, Claude Desktop, etc.) upload audio, run batch transcriptions, and work with the results — summaries, minutes, sections, notes, and transcript Q&A chats.
Setup
Get a Transcribe API key: log into https://www.transcribe.gov.sg/ and visit https://www.transcribe.gov.sg/dev_api_key (or use the
POST /auth/otps+POST /auth/tokens+POST /auth/apikeysflow if your org isn't on WOG-AD). API keys are valid for 90 days.Install the package:
pip install -e .Set the required environment variables:
TRANSCRIBE_API_KEY— your 90-day API keyTRANSCRIBE_EMAIL— the email address the API key was issued toTRANSCRIBE_BASE_URL— optional, defaults tohttps://core.transcribe.gov.sgTRANSCRIBE_API_VERSION— optional, defaults to3.0
Related MCP server: Open Router Audio Transcription MCP
Registering with Claude Code
claude mcp add transcribe \
--env TRANSCRIBE_API_KEY=your-api-key \
--env TRANSCRIBE_EMAIL=you@domain.gov.sg \
-- transcribemcpOr add directly to .mcp.json:
{
"mcpServers": {
"transcribe": {
"command": "transcribemcp",
"env": {
"TRANSCRIBE_API_KEY": "your-api-key",
"TRANSCRIBE_EMAIL": "you@domain.gov.sg"
}
}
}
}Registering with Claude Desktop
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"transcribe": {
"command": "transcribemcp",
"env": {
"TRANSCRIBE_API_KEY": "your-api-key",
"TRANSCRIBE_EMAIL": "you@domain.gov.sg"
}
}
}
}Scope
Covers batch transcription (workspaces, projects, transcriptions), summaries, minutes, sections, notes, and chat-based Q&A over a transcript. Live Transcription is not supported — it requires real-time WebRTC audio streaming, which doesn't fit an MCP tool-call model. See docs/superpowers/specs/2026-07-05-transcribe-mcp-server-design.md for the full design rationale.
Development
pip install -e ".[dev]"
pytestThis server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for Speech-to-Text
MCP server for RiverScript, an AI transcription platform - fetches transcripts shared via a link.
An MCP server that provides congressional transcripts
MCP server for the FFmpeg Micro video transcoding API — create, monitor, download transcodes.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server for audio transcription with speaker diarization. Transcribes MP3/WAV files using Faster-Whisper and pyannote.audio, outputs markdown with speaker labels, timestamps, summaries, and action items.1MIT
- AlicenseAqualityCmaintenanceMCP server for audio transcription using OpenRouter models, supporting verbatim, cleaned, and custom transcription modes.28 npm1MIT
- AlicenseNot gradedqualityAmaintenanceMCP server that enables audio transcription from files (wav, mp4, mp3, flac) or microphone recording, with dynamic tool selection and enterprise-grade security.2MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that converts videos, audio, and meeting recordings into structured transcripts and summaries with multi-backend ASR and automatic fallback.MIT