Open-source text-to-speech tool that converts long texts and novels into audio, with subtitles and multi-voice character dubbing.
JJosephph/ms-edge-tts-gui
Free, open-source Windows desktop app that turns text, scripts and documents into MP3 audio using Microsoft Edge online voices, with no API key.
- Stars
- 52
- Forks
- 6
- Open issues
- 1
- Last commit
- yesterday
What is it?
Edge TTS Voice Studio is a Windows desktop client for Microsoft Edge text-to-speech voices. You paste an article, script or subtitle draft, or import txt, md, docx and pdf files, and export the result as an MP3. It needs no API key and is built on the open-source edge-tts library.
The app offers three work modes: Normal for one full text, Page for splitting content on [分页] markers into one audio per page, and Line for one audio file per non-empty line. Normal mode can also batch-process multiple files with per-file voice and pause settings, and completed items are kept when you retry.
For editing and review, it provides independent sentence pauses in milliseconds, optional SRT subtitles, a timeline JSON with sentence start and end times, live sentence highlighting during playback, and a result window with per-row playback, draggable progress and regeneration. A Language, Gender, Voice picker, a bilingual Chinese and English interface, proxy-aware network checks and stall recovery round out the tool.
Key features
- 01Converts pasted text or txt, md, docx and pdf files into MP3 audio without an API key.
- 02Three modes: full-text, per-page and per-line audio generation.
- 03Batch upload in Normal mode with per-file voice, pause and subtitle settings.
- 04Independent sentence pauses in milliseconds and optional SRT subtitles.
- 05Timeline JSON with sentence timing and live highlighting during playback.
- 06Language, gender and voice picker with a Chinese and English interface.
Use cases
- Narrating articles or documents into audio.
- Producing voiceover for short videos, explainers and line-by-line narration.
- Generating SRT subtitles aligned with the final audio for video editing.
- Shadowing or reviewing foreign-language text sentence by sentence.
Quick start
- 1
Download EdgeTTSGui-Setup.exe from the Releases page
- 2
Run the installer and choose any install folder
- 3
Paste your text, choose a voice, and click Generate audio
Things to know
- Windows only; the README lists no macOS or Linux build.
- Licensed under GPL-3.0-or-later, a copyleft license.
- Needs an internet connection to reach Microsoft Edge online voices.
In collections
Topics
FAQ
- What is ms-edge-tts-gui?
- Free, open-source Windows desktop app that turns text, scripts and documents into MP3 audio using Microsoft Edge online voices, with no API key. Edge TTS Voice Studio is a Windows desktop client for Microsoft Edge text-to-speech voices. You paste an article, script or subtitle draft, or import txt, md, docx and pdf files, and export the result as an MP3. It needs no API key and is built on the open-source edge-tts library.
- Is ms-edge-tts-gui free to use? What license does it have?
- ms-edge-tts-gui is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
- Is ms-edge-tts-gui still maintained?
- Actively maintained. The last commit to ms-edge-tts-gui was on Oct 21, 2026.
- What can I use ms-edge-tts-gui for?
- Narrating articles or documents into audio. Producing voiceover for short videos, explainers and line-by-line narration. Generating SRT subtitles aligned with the final audio for video editing. Shadowing or reviewing foreign-language text sentence by sentence.
- How do I install ms-edge-tts-gui?
- Download EdgeTTSGui-Setup.exe from the Releases page Run the installer and choose any install folder Paste your text, choose a voice, and click Generate audio
- Where can I get ms-edge-tts-gui?
- The source code and installation instructions are on GitHub: https://github.com/JJosephph/ms-edge-tts-gui
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Desktop and web app that converts EPUB, PDF, text and subtitle files into audio with synced subtitles, using Kokoro-82M TTS.
AI video agent for macOS and Windows that edits videos on an editable timeline: transcribe, subtitle, translate, dub, cut and animate.
An AI agent skill that drives the desktop JianYing (Chinese CapCut) Pro to automate video editing from natural-language instructions.
AI-powered tool that writes video narration scripts and automatically edits videos, with voiceover and subtitle generation, for commentary-style content.
Open-source tool that translates video into another language, with speech recognition, subtitle translation, AI dubbing and audio-video synthesis.