clova-speech-lecture-mcp
Servidor MCP de CLOVA Speech Lecture
Servidor MCP para STT y resumen de grabaciones de conferencias. Llama a las API de Naver CLOVA Speech / CLOVA Studio desde el agente Google ADK.
Herramientas proporcionadas
Nombre de la herramienta | Descripción | Situación adecuada |
| STT síncrono (60 segundos o menos) | Clips cortos, pruebas |
| Envío de STT asíncrono (conferencia completa) | Conferencias de decenas de minutos a horas |
| Consulta de resultados de STT asíncrono | Sondeo después de submit |
| Resumen de la transcripción de la conferencia | Después de completar la transcripción |
Related MCP server: Whisper Valet
Introducción
1. Emisión de claves API
CLOVA Speech (STT)
Inicie sesión en Naver Cloud Platform
AI Services → CLOVA Speech → Solicitar uso
Copie la Secret Key después de crear el servicio
CLOVA Studio (Resumen)
AI Services → CLOVA Studio → Solicitar uso
Crear una aplicación en Playground
Copie la clave API y el ID de la aplicación
2. Configuración de .env
cp .env .env.local # 실제 값으로 수정CLOVA_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_ID3. Ejecución
# Docker
docker-compose up -d
# 로컬 실행
pip install -r requirements.txt
python app/main.py4. Conexión del agente ADK
# agent.py 예시
tools = [
MCPToolset(
connection_params=SseServerParams(url="http://localhost:8002/sse")
)
]Flujo de procesamiento de conferencias
[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]Formatos de audio compatibles
.wav .mp3 .flac .m4a .aac .ogg
Idiomas compatibles
Código (corto) | Código (largo) | Idioma |
|
| Coreano |
|
| Inglés |
|
| Japonés |
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
Pronunciation assessment, phoneme scoring, speaker voice ID, audio transcription, speech synthesis.
Pronunciation scoring, speech-to-text, and text-to-speech for language learning
Transcribe audio and video into speaker-labelled transcripts, subtitles, clips, and cited Q&A.
Transcribe, summarize and analyze audio with AssemblyAI speech-to-text and Speech Understanding.
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides accurate meeting transcription with speaker diarization and multilingual support, allowing users to submit audio URLs, poll transcription status, get transcripts, and summarize via MCP tools in their IDE.81MIT
- AlicenseAqualityDmaintenanceEnables automated audio restoration, transcription, and speaker diarization via MCP tools for queuing files, monitoring progress, and retrieving speaker-labeled transcripts.9MIT

Tapra MCP serverofficial
AlicenseAqualityBmaintenanceEnables transcription and subtitling of Tunisian Derja mixed with French and English, speech and voiceover generation, translation, and Arabizi–Arabic script conversion inside MCP clients. It also supports speaker diarization, subtitle translation, transcript search, and audio editing.16488 npmMIT
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