Moyf/moys-asr-workflow

Moy 的 ASR 字幕生成工作流及编辑器，简称 MAW

What it solves

It streamlines the process of creating subtitles for local media files by automating the transcription of audio to text and providing a professional editing environment. It bridges the gap between raw AI transcription (which often requires manual correction) and the final exported subtitle file (SRT, ASS).

How it works

The workflow consists of three main stages: transcription, editing, and export. Users provide an API key for a chosen ASR (Automatic Speech Recognition) service (such as Qwen, Fun-ASR, Soniox, or OpenAI), and the software handles the media upload and transcription. The resulting data is saved as a .mosp project file, which is then opened in the MAWE Server editor for precise adjustments using waveform positioning and visual previews. Finally, the subtitles are exported to standard formats.

Who it’s for

Content creators, video editors, and translators who need an efficient way to generate and refine AI-transcribed subtitles for their videos.

Highlights

  • Multi-Provider Support: Integrates with various ASR services including Qwen, Fun-ASR, Soniox, Tencent Cloud, and OpenAI.
  • Advanced Editing: The MAWE editor features waveform-based positioning, splitting/merging of segments, and silence gap handling.
  • Dual-Track Subtitles: Supports importing a second subtitle track for side-by-side editing, binding/unbinding tracks, and cross-track snapping.
  • Automation Ready: Includes a public CLI for batch processing and AI-driven automation.
  • Local Options: Offers experimental support for local ASR models like Qwen3-ASR, FunASR, and Faster-Whisper.

Related

  • Project
    wavlab-speech/versa

    A comprehensive toolkit providing a unified interface to over 90 metrics for evaluating the quality, intelligibility, and technical properties of speech and audio.

  • Project
    misyaguziya/VRCT

    VRCT is a translation and transcription tool designed to help VRChat users communicate across different languages via real-time audio-to-text and chat integration.

  • Project
    jasoncheng7115/jt-live-whisper

    A fully local AI toolkit for real-time speech transcription, translation, and meeting summarization that works across any system audio source without cloud APIs.

  • Project
    smallnest/pigo

    pigo is a Go‑based CLI AI coding assistant (a clone of the pi agent) that can read/write files, run shell commands, fetch web content, and interact with many LLM providers. It works in headless script mode or an interactive REPL, supports tool‑level allow/deny lists, project trust, prompt templates, skills, plugins, self‑update, and provides a Go SDK for embedding.