An edge-tts alternative that works offline
edge-tts is a popular Python package that sends text to the online read-aloud service behind Microsoft Edge and saves the speech it returns. It is free and the voices are good, but it needs the internet, it is not an official API, and it can stop working whenever the service changes.
SuperClonica takes a different route: a free engine that voices text on your own computer, offline, with stock voices, character voices from the catalog and voices trained from your own recordings. This page compares the two honestly.
Two different setups
One borrows an online service; the other is an engine you install and keep.
- edge-tts: text goes to an online service; many voices and languages; unofficial, so it can break or be limited at any time.
- SuperClonica: the model runs locally after a one-time download of about 385 MB; nothing is sent anywhere.
- SuperClonica voices speak 31 languages; Chinese is not supported yet, while edge-tts offers Chinese voices.
- SuperClonica adds character voices and voices trained from your own recordings.
When edge-tts is fine
For a quick personal script with an internet connection, or when you need Chinese or a language Supertonic 3 does not speak, edge-tts is a reasonable choice, and SuperClonica does not replace its range of languages.
When SuperClonica fits better
The same text, voice and seed always give the same audio, which makes builds and caches predictable.
- Your scripts must work offline or in a closed network.
- Your texts are private and should not leave the machine.
- You build a product and need a dependency that will not disappear with a service change.
- You want character voices, a consistent brand voice or your own trained voice.
Switch in a few lines
Install the engine with python -m pip install superclonica-cpu. On the command line, voice a text file straight to MP3: superclonica --text-file script.txt --voice F1 --lang en --output out.mp3. In Python, after from superclonica import Superclonica and tts = Superclonica(), replace your edge-tts call with audio, rate = tts.synthesize(text, voice="F1", lang="en"); tts.save("out.wav", audio). Long texts are split at natural pauses and joined into one file. Before you switch, try a voice on its page with a line of 30 to 100 characters, free and without an account.
What it costs
The engine and the ten stock voices of the model are free, and several catalog voices are free too. Other voices are bought once and stay yours. There is no per-request fee and no service to depend on: once installed, it works without the internet.