FFVoice vs Local Speech-to-Text

Offline speech-to-text and speaker diarization using on-device Whisper processing.

Provides local speech-to-text transcription using whisper.cpp with automatic audio format conversion, intelligent chunking for long files, speaker diarization, and multiple output formats for private transcription workflows without cloud dependencies.

MCP Servers

MCP Servers

3

—

—

—

TypeScript

—

MIT

—

—

53

5