English Text to Speech
Turn English text into natural speech with AI voices. 93 voices. Free, no signup — download as MP3 or WAV.
Wrap your text in SSML tags for precise control:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Tags the selected model understands — click to drop one into your text where it happens:
This model reads plain text, so inline tags are ignored. For tag-based emotion, switch to an expressive model like Orpheus or Bark.
Define custom pronunciations (word = pronunciation):
About English text to speech
English text-to-speech spans a wide accent range — General American, Received Pronunciation, Scottish, Irish, Australian, Indian and others — and the choice materially changes vowel quality and rhythm. English is stress-timed, so a natural voice must reduce unstressed syllables to schwa and place sentence stress correctly rather than giving every word equal weight. Its deep orthography (where "ough" reads six different ways) makes a strong pronunciation dictionary and number/abbreviation normalization the hardest part of good English synthesis.
Sample — English
“The quick brown fox jumps over the lazy dog while the morning sun rises slowly above the quiet valley.”
- Native name
- English
- Speakers
- 1.5 billion total speakers (about 380 million native)
- Language family
- West Germanic branch of Indo-European
- Script
- Latin
- Spoken in
- United States, United Kingdom, Canada, Australia, India, Nigeria, Ireland, New Zealand, South Africa
