clova-speech-lecture-mcp
Enables speech-to-text transcription and summarization of lecture audio using Naver CLOVA APIs. Provides MCP tools for short and long audio processing with summarization.
README
CLOVA Speech Lecture MCP Server
강의 녹음 STT 및 요약을 위한 MCP 서버입니다.
Google ADK 에이전트에서 네이버 CLOVA Speech / CLOVA Studio API를 호출합니다.
제공 툴
| 툴 이름 | 설명 | 적합한 상황 |
|---|---|---|
transcribe_short |
동기 STT (60초 이하) | 짧은 클립, 테스트 |
transcribe_lecture_submit |
비동기 STT 제출 (강의 전체) | 수십 분~수 시간 강의 |
get_transcription_result |
비동기 STT 결과 조회 | submit 후 폴링 |
summarize_lecture |
강의 전사본 요약 | 전사 완료 후 |
시작하기
1. API 키 발급
CLOVA Speech (STT)
- 네이버 클라우드 플랫폼 로그인
- AI Services → CLOVA Speech → 이용 신청
- 서비스 생성 후 Secret Key 복사
CLOVA Studio (요약)
- AI Services → CLOVA Studio → 이용 신청
- Playground에서 앱 생성
- API 키 및 앱 ID 복사
2. .env 설정
cp .env .env.local # 실제 값으로 수정
CLOVA_SPEECH_API_KEY=실제_키_입력
CLOVA_STUDIO_CLIENT_ID=실제_Client_ID
CLOVA_STUDIO_CLIENT_SECRET=실제_Client_Secret
CLOVA_STUDIO_APP_ID=실제_앱_ID
3. 실행
# Docker
docker-compose up -d
# 로컬 실행
pip install -r requirements.txt
python app/main.py
4. ADK 에이전트 연결
# agent.py 예시
tools = [
MCPToolset(
connection_params=SseServerParams(url="http://localhost:8002/sse")
)
]
강의 처리 플로우
[강의 오디오 파일]
↓
transcribe_lecture_submit(file_path, enable_diarization=True)
↓ (task_id 반환)
get_transcription_result(task_id) ← 완료까지 자동 폴링
↓ (full_text 반환)
summarize_lecture(text)
↓
[요약문 + 키워드]
지원 오디오 형식
.wav .mp3 .flac .m4a .aac .ogg
지원 언어
| 코드 (단문) | 코드 (장문) | 언어 |
|---|---|---|
Kor |
ko-KR |
한국어 |
Eng |
en-US |
영어 |
Jpn |
ja-JP |
일본어 |
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.