ms-edge-tts-gui

Project Overview

Edge TTS Voice Studio is a free, open-source Windows desktop application (MIT License, developer WangYufan). It turns articles, scripts, and subtitle texts into natural MP3 audio without requiring an API key. It offers Normal, Per-page, and Per-line working modes, with independent sentence pauses, real silence at line ends, SRT subtitles, timeline JSON, per-sentence preview highlighting, draggable playback progress, and batch ZIP export. The interface can switch between Chinese and English at any time.

Key Features

• Generate, preview, and save: One-click full-text audio generation; preview or save/download at any time after generation
• Three working modes: Normal mode reads the full text; Per-page mode generates one audio per [分页] marker; Per-line mode generates one audio per non-empty line
• Real-time progress: Displays approximate 0–100% progress during generation
• Timeline JSON + preview highlighting: Automatically packages a ZIP (MP3 + .timeline.json with per-sentence start/end times); the currently spoken sentence is highlighted in real time during preview
• Result table browser: Batch results displayed per row with preview and regenerate operations
• Draggable playback timeline: Each row shows elapsed/total seconds with a draggable green slider
• Independent sentence pauses: Precisely set silence intervals between sentences in milliseconds
• Line-end pauses: Per-line mode can append real silence after the entire line's audio
• SRT subtitles: Each sentence corresponds to one subtitle, with timing strictly matching the final audio
• Network protection: Shows network diagnostic information during generation

Target Audience

• Users who need text-to-speech conversion
• Users doing narration, video editing, shadowing practice, and batch dubbing
• Windows users

Quick Start

1. Download the latest version from the Releases page
2. Install and launch the app
3. Enter or paste text, select working mode and voice parameters
4. Click generate; preview or save/download when complete

Core Advantages

• Free and open source, MIT License
• No API key required, uses Microsoft Edge TTS service
• Feature-rich with three working modes, SRT subtitles, timeline JSON, and more
• Chinese/English interface switchable at any time

System Requirements

• OS: Windows