sttai-mcp
Allows downloading and transcribing YouTube videos by URL, then querying and analyzing the resulting transcript with STT.ai tools.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
STT.ai MCP Server
Model Context Protocol server for STT.ai. Lets Claude Desktop, Cursor, and any other MCP-compatible client transcribe audio/video, manage transcripts, and run AI features over them.
Differentiator vs other STT MCP servers (Otter, Fireflies, Granola, Read AI): those are read-only over stored transcripts. This one also exposes transcribe_url and chat_with_transcript, so Claude can transcribe a YouTube link and immediately query the result in one conversation.
Tools
Tool | What it does |
| List your past transcripts (paginated, filter by status) |
| Fetch one transcript with segments, speakers, summary, metadata |
| Export as text/srt/vtt/json/csv |
| Download + transcribe any URL (YouTube, podcast, direct file) |
| AI summary (cached or regenerated) |
| Sentiment, topics, entities, action items, questions, PII |
| Blog posts, social media, study guides, flashcards, etc. |
| RAG Q&A with source citations (segment IDs + timestamps) |
| Available transcription models with WER benchmarks |
| Supported languages |
Related MCP server: Voxloom MCP Server
Install
pip install sttai-mcpConfigure
Get your STT.ai API key at https://stt.ai/account/#developer.
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"stt-ai": {
"command": "sttai-mcp",
"env": {
"STT_API_KEY": "your-api-key-here"
}
}
}
}Restart Claude Desktop. The STT.ai tools should appear.
Cursor
Settings → MCP → Add new MCP server:
{
"stt-ai": {
"command": "sttai-mcp",
"env": { "STT_API_KEY": "your-api-key-here" }
}
}Run directly
STT_API_KEY=your-key sttai-mcpThe server speaks MCP over stdio.
Examples
In Claude Desktop, after configuring:
"Transcribe https://www.youtube.com/watch?v=dQw4w9WgXcQ and summarize the key points."
Claude will call transcribe_url, then summarize_transcript on the result.
"What are my last 5 transcripts about?"
Claude calls list_transcripts(limit=5) and reads each title.
"In transcript abc123, what did the speaker say about pricing?"
Claude calls chat_with_transcript("abc123", "what did they say about pricing?") and gets an answer with timestamped sources.
Repo
License: MIT
Maintained by STT.ai.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for RiverScript, an AI transcription platform - fetches transcripts shared via a link.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
An MCP server that gives any LLM or agent clean YouTube transcripts on demand: a single video, a whole channel, or a playlist, plus AI cleanup of auto-generated captions. API-key auth, credit-based, same backend as the public v1 API. Get a free API key with 25 free credits at youtubetranscriptdownload.com/account.
Search, read, analyze and create HappyScribe transcripts and meeting notes from any MCP client
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to submit and manage durable long-form audio transcription jobs, and read or export structured transcripts via MCP tools.1MIT
- AlicenseAqualityCmaintenanceEnables an assistant to transcribe video or podcast recordings, then read, search, summarize, and manage the resulting transcripts through MCP tools.10MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants and MCP clients to ingest audiovisual media from local files or yt-dlp-supported URLs, producing timestamped transcripts and scene-selected keyframes with exact-frame drill-down and transcript search.102 PyPI3MIT

AssemblyAI MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceEnables MCP-capable agents to submit and retrieve audio transcriptions, apply speech understanding such as translation, speaker identification, summaries and action items, and enforce guardrails including PII redaction and content moderation.2MIT