Verified project record

rany2/edge-tts

edge-tts is a Python module and CLI toolset that synthesizes speech and subtitles from text using Microsoft Edge's online text-to-speech service, without requiring Microsoft Edge, Windows, or an API key. It takes text as input and produces audio files (e.g., MP3) and subtitle files (e.g., SRT).

Project overview

It gives developers and general users command-line and Python access to Microsoft Edge's online TTS voices from Windows, Linux, or macOS without an API key, with no GPU required.

Project type: Audio & Speech · Infrastructure
Use cases: Audio & Speech
Deployment: Refer to project documentation
License: License pending

Best for

Developers who want to call Microsoft Edge's online TTS service from Python code or the CLI without an API key.
General users on Windows, Linux, or macOS who need MP3 audio and SRT subtitles from text and do not have Microsoft Edge installed.
Users without a GPU, since inference happens on Microsoft's online service and no GPU is required locally.

Key capabilities

The `edge-tts` command synthesizes speech to media files (e.g., MP3) and subtitle files (e.g., SRT).
The `edge-playback` command plays synthesized speech immediately, with subtitles.
The edge-tts service can be used directly from Python code.
Available voices can be changed and listed using the `--voice` and `--list-voices` options.
Rate, volume, and pitch of generated speech can be adjusted via command-line options.

Limitations and risks

Custom SSML support was removed because Microsoft prevents use of any SSML that could not be generated by Microsoft Edge itself.
`edge-playback` requires installation of the `mpv` command-line player, except on Windows.

Getting started

Install via `pip install edge-tts` (pip or pipx); setup difficulty is documented as easy.

Alternatives and comparisons

A generative AI framework for building and deploying speech models including Text-to-Speech, suitable when self-hosted model training and deployment are needed rather than a remote TTS service.
Covers the opposite direction of the pipeline (speech recognition and translation) rather than text-to-speech; relevant only if speech-to-text needs coexist.
A C++ toolkit for building speech recognition systems, addressing speech-to-text rather than text-to-speech.

Project comparisons

Evidence and sources

README: `edge-tts` is a Python module that allows you to use Microsoft Edge's online text-to-speech service from within your Python code or using the provided `edge-tts` or `edge-playback…
GitHub project description: Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
README: $ edge-tts --text "Hello, world!" --write-media hello.mp3 --write-subtitles hello.srt If you wish to play it back immediately with subtitles, you could use the `edge-playback` com…
README: You can change the voice used by the text-to-speech service by using the `--voice` option. The `--list-voices` option can be used to list all available voices.
README: You can change the rate, volume and pitch of the generated speech by using the `--rate`, `--volume` and `--pitch` options.

Source updated at: 2026-07-23T18:19:40Z

Open original GitHub project