About this website
Anxinzhuan is an offline speech-to-text application for Windows, macOS, Linux and Android. It processes audio and video recordings locally. Users can import several files and let the queue transcribe them automatically, then review the transcript with timestamps and speaker labels. It helps organize meeting recordings, interviews and course material or create a first subtitle draft. Files and transcripts remain on the user’s device. MCP integration connects compatible tools to the local workflow.
Key features
- Local offline speech-to-text processing
- Batch audio and video import queue
- Speaker labels and timestamps
- MCP integration for local workflows
Who is this website for?
People organizing meeting recordings, interviews, course videos and private audio or video material.
What can visitors do here?
Download the app, import a meeting recording or several course videos, run local transcription, then review the resulting text using timestamps and speaker labels.
What makes it different?
Audio, video and transcripts remain on local devices. Batch queuing and MCP integration support repeatable transcription workflows.
