GUIDE

English text to speech: AI voices that read English

English is one of the 31 languages of Supertonic 3, the open text-to-speech model behind SuperClonica, so every voice in the catalog reads English: narrators, male and female voices, characters from games, anime, cartoons and films. You can hear any of them say your own English line for free, and voice long English texts offline on your own computer without a character limit.

This guide explains how to get the best English from it, honestly: how to write the text, what the engine does with numbers, what accent to expect and how to get the voice you need.

Try any voice in English for free

On the page of any voice, choose English next to the text field, type a phrase of 30 to 100 characters and press Voice it. You hear your words in that voice in a few seconds and can download the recording. No account is needed.

Write English the way it should sound

Short sentences with clear punctuation sound the most natural.

  • Numbers, dates and units can stay as digits: the engine spells them as English words.
  • Chat shorthand like “pls”, “btw” or “idk” is written out as words for you.
  • Unusual abbreviations: write them the way they should be said (“F B I” or “the agency”) and check them in the free test.
  • For words spelled the same but said differently (“read”, “lead”), make the sentence clear; the model reads the whole phrase at once.

What accent to expect

Dozens of voices in the catalog were made from English recordings: Jarvis, Darth Vader, Batman, Billy Butcher, SpongeBob, Rick and Morty and more. They sound the most natural in English. The voices made from Russian recordings read English too, with a slight Russian accent that suits characters and parodies. Filter the catalog by the language of the recording to see the English ones.

Get a voice recorded in English

For a native English voice of your own, train one from a clean recording of 5 to 10 seconds in English, your own voice or a speaker who agreed, in the studio on a computer with an NVIDIA graphics card. No graphics card? Order the voice on the exchange: an author trains it from your recording, and you pay only after you accept it.

Unlimited English offline

For long texts, download the voice file and install the free SuperClonica engine: python -m pip install superclonica-cpu. Then voice a text file with one command: superclonica --text "$(cat text.en.txt)" --voice voice.json --lang en --output en.wav. It runs on an ordinary processor, offline, with no character limit and no monthly fee.