mcp_openai_transcribe
Convert audio to text using the OpenAI Whisper API, supporting multiple languages and customizable prompts for enhanced transcription accuracy.
Instructions
OpenAI Whisper API를 사용하여 음성을 텍스트로 변환합니다. 변환된 텍스트를 반환합니다.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| audioPath | Yes | 변환할 오디오 파일 경로 | |
| language | No | 오디오 언어 (예: ko, en, ja) | |
| model | No | 사용할 모델 (예: whisper-1) | |
| prompt | No | 인식을 도울 힌트 텍스트 |
Input Schema (JSON Schema)
You must be authenticated.
Other Tools from Ontology MCP
- mcp_gemini_chat_completion
- mcp_gemini_create_image
- mcp_gemini_edit_image
- mcp_gemini_generate_image
- mcp_gemini_generate_images
- mcp_gemini_generate_multimodal_content
- mcp_gemini_generate_text
- mcp_gemini_generate_videos
- mcp_gemini_list_models
- mcp_http_request
- mcp_imagen_generate
- mcp_ollama_chat_completion
- mcp_ollama_list
- mcp_ollama_pull
- mcp_ollama_rm
- mcp_ollama_run
- mcp_ollama_show
- mcp_ollama_status
- mcp_openai_chat
- mcp_openai_embedding
- mcp_openai_image
- mcp_openai_transcribe
- mcp_openai_tts
- mcp_sparql_execute_query
- mcp_sparql_get_resource_info
- mcp_sparql_list_graphs
- mcp_sparql_list_repositories
- mcp_sparql_update
Related Tools
- @Ichigo3766/audio-transcriber-mcp
- @bigdata-coss/agent_mcp
- @PhialsBasement/KoboldCPP-MCP-Server
- @mamertofabian/elevenlabs-mcp-server
- @vmehta14/whissle-mcp