Edge TTS is a Python library and command-line tool that gives you access to Microsoft Edge’s online text-to-speech service — the same neural voices behind Edge’s Read Aloud feature — from any Python program or terminal, without needing Microsoft Edge or Windows installed. It has collected about 12,300 stars on GitHub and is actively maintained through 2026.
Microsoft’s online speech service offers hundreds of high-quality neural voices across a wide range of languages and locales, but it is normally only reachable through the Edge browser. Edge TTS speaks to that service directly, so a single command or a few lines of Python can turn text into natural-sounding speech and save it as an MP3, stream it, or capture word-boundary timing data for subtitles and highlighting. Developers use it to voice videos, podcasts, audiobooks, language-learning material, accessibility tools and voice assistants, often as the free speech layer in a larger pipeline. Because the synthesis happens in Microsoft’s cloud, results are fast and consistent on modest hardware, and the tool itself stays lightweight — a pure Python package installable from PyPI with both a module API and the edge-tts and edge-playback command-line utilities.
Edge TTS is free and open source, and the Microsoft speech service it connects to currently costs nothing to use through this tool. There are no paid tiers; your only consideration is that it depends on an online service rather than running models locally.
Edge TTS is for creators and developers who need large volumes of good-quality speech synthesis at zero cost — narrating videos, generating audiobooks, prototyping voice interfaces or adding speech output to applications — and are comfortable with synthesis running through Microsoft’s online service.