MCP Server Whisper
未认领An MCP Server for audio transcription using OpenAI
安装
$
bunx dotenv-cli -- claude工具（13 个）
analytical
Adds analysis of speech patterns and key points
chat_with_audio
Interactive audio analysis using GPT-4o audio models:
compress_audio
Compresses audio files that exceed size limits
convert_audio
Converts audio files to supported formats (mp3 or wav)
create_audio
Generate text-to-speech audio using OpenAI's TTS API:
detailed
Includes tone, emotion, and background details
get_latest_audio
Gets the most recently modified audio file with model support info
list_audio_files
Lists audio files with comprehensive filtering and sorting options:
professional
Creates formal, business-appropriate transcriptions
storytelling
Transforms the transcript into a narrative form
Text-to-Speech
transcribe_audio
Advanced transcription using OpenAI's models:
transcribe_with_enhancement
Enhanced transcription with specialized templates: