Access Microsoft Edge online text-to-speech from Python without needing the browser.
Use Microsoft Edge's online text-to-speech service directly from Python and the command line.
edge-tts is a Python module and command-line tool allowing you to tap into Microsoft Edge's online text-to-speech engine without installing the browser itself. It suits developers and researchers who need to quickly synthesize speech, create audio files, or generate subtitles.
The tool provides Python bindings and CLI commands to synthesize speech using Microsoft Edge's TTS service, letting you specify voice models, rates, volumes, and pitches. It also exports corresponding .srt subtitle files alongside your generated media output.
It suits developers building study aids, language researchers, and students automating text-to-speech workflows in Python. It does not suit those seeking local offline models or complex custom SSML injections, as Microsoft restricts unsupported SSML tags.
Interact with Edge's TTS service directly through your Python code or terminal commands.
Automatically export .srt subtitle files alongside your generated media output.
List available neural voices and adjust rate, volume, and pitch parameters.
Use the edge-playback command to stream and listen to synthesized speech immediately.
The tool is free to use, and the repository does not state a specific license. The only cost is your own internet access and time to run it.
880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
No, edge-tts connects to Microsoft Edge's online service from Python without needing the browser installed.
Yes, using the --write-subtitles flag alongside --write-media will generate an SRT file.
Microsoft prevents the use of any SSML that could not be generated by Microsoft Edge itself, limiting customization.
See Zekai first in Google