Local STT

소개

Leverages whisper.cpp to deliver high-performance, local speech-to-text transcription. Optimized for Apple Silicon, this server offers fast processing speeds and low memory usage, ensuring privacy and efficiency. It supports speaker diarization, universal audio formats, and multiple output formats, providing a comprehensive solution for speech recognition needs.

주요 기능

• 100% Local Processing for complete privacy
• Universal Audio Support with automatic conversion
• Multiple Output Formats (txt, json, vtt, srt, csv)
• Apple Silicon Optimized for 15x+ real-time transcription speed
• 1 GitHub stars
• Speaker Diarization to identify and separate multiple speakers

사용 사례

• Transcribing audio recordings locally without relying on cloud services
• Converting various audio formats to text for accessibility or archival purposes
• Analyzing audio content with speaker diarization for identifying different speakers