English Text to Speech

75 free English AI voices

SpeakScribe has 75 English voices: 28 Studio voices that run on our own servers and 47 Global Microsoft neural voices. They cover 14 accents, from American and British to Indian, Nigerian, Kenyan and Philippine English, so start by choosing the accent your viewers expect.

Alloy

Female · American

STUDIO
Use voice

Aoede

Female · American

STUDIO
Use voice

Bella

Female · American

STUDIO
Use voice

Heart

Female · American

STUDIO
Use voice

Jessica

Female · American

STUDIO
Use voice

Kore

Female · American

STUDIO
Use voice

Nicole

Female · American

STUDIO
Use voice

Nova

Female · American

STUDIO
Use voice

River

Female · American

STUDIO
Use voice

Sarah

Female · American

STUDIO
Use voice

Sky

Female · American

STUDIO
Use voice

Adam

Male · American

STUDIO
Use voice

Echo

Male · American

STUDIO
Use voice

Eric

Male · American

STUDIO
Use voice

Fenrir

Male · American

STUDIO
Use voice

Liam

Male · American

STUDIO
Use voice

Michael

Male · American

STUDIO
Use voice

Onyx

Male · American

STUDIO
Use voice

Puck

Male · American

STUDIO
Use voice

Santa

Male · American

STUDIO
Use voice

Alice

Female · British

STUDIO
Use voice

Emma

Female · British

STUDIO
Use voice

Isabella

Female · British

STUDIO
Use voice

Lily

Female · British

STUDIO
Use voice

Daniel

Male · British

STUDIO
Use voice

Fable

Male · British

STUDIO
Use voice

George

Male · British

STUDIO
Use voice

Lewis

Male · British

STUDIO
Use voice

Ava

Female · American

GLOBAL
Use voice

Emma

Female · American

GLOBAL
Use voice

Jenny

Female · American

GLOBAL
Use voice

Aria

Female · American

GLOBAL
Use voice

Michelle

Female · American

GLOBAL
Use voice

Ana

Female · American

GLOBAL
Use voice

Ava

Female · American · Multilingual

GLOBAL
Use voice

Emma

Female · American · Multilingual

GLOBAL
Use voice

Andrew

Male · American

GLOBAL
Use voice

Brian

Male · American

GLOBAL
Use voice

Christopher

Male · American

GLOBAL
Use voice

Eric

Male · American

GLOBAL
Use voice

Guy

Male · American

GLOBAL
Use voice

Roger

Male · American

GLOBAL
Use voice

Steffan

Male · American

GLOBAL
Use voice

Andrew

Male · American · Multilingual

GLOBAL
Use voice

Brian

Male · American · Multilingual

GLOBAL
Use voice

Libby

Female · British

GLOBAL
Use voice

Maisie

Female · British

GLOBAL
Use voice

Sonia

Female · British

GLOBAL
Use voice

Ryan

Male · British

GLOBAL
Use voice

Thomas

Male · British

GLOBAL
Use voice

Natasha

Female · Australian

GLOBAL
Use voice

William

Male · Australian · Multilingual

GLOBAL
Use voice

Clara

Female · Canadian

GLOBAL
Use voice

Liam

Male · Canadian

GLOBAL
Use voice

Neerja

Female · Indian

GLOBAL
Use voice

Neerja (expressive)

Female · Indian

GLOBAL
Use voice

Prabhat

Male · Indian

GLOBAL
Use voice

Emily

Female · Irish

GLOBAL
Use voice

Connor

Male · Irish

GLOBAL
Use voice

Molly

Female · New Zealand

GLOBAL
Use voice

Mitchell

Male · New Zealand

GLOBAL
Use voice

Rosa

Female · Philippine

GLOBAL
Use voice

James

Male · Philippine

GLOBAL
Use voice

Luna

Female · Singaporean

GLOBAL
Use voice

Wayne

Male · Singaporean

GLOBAL
Use voice

Yan

Female · Hong Kong

GLOBAL
Use voice

Sam

Male · Hong Kong

GLOBAL
Use voice

Asilia

Female · Kenyan

GLOBAL
Use voice

Chilemba

Male · Kenyan

GLOBAL
Use voice

Ezinne

Female · Nigerian

GLOBAL
Use voice

Abeo

Male · Nigerian

GLOBAL
Use voice

Imani

Female · Tanzanian

GLOBAL
Use voice

Elimu

Male · Tanzanian

GLOBAL
Use voice

Leah

Female · South African

GLOBAL
Use voice

Luke

Male · South African

GLOBAL
Use voice

How English is written — and what to type so the voice reads it right

Spelling does not change the accent. Typing 'colour' will not make an American voice sound British, so pick the voice that matches your audience.

Heteronyms are the main source of wrong readings: words such as read, lead, live, record, wind and tear are spelled the same but pronounced differently. The voice guesses from context, so rephrase the sentence rather than respelling the word.

  • Replace 'I have read it' with 'I finished reading it' when the past tense is meant.

Dates, abbreviations and acronyms in English scripts

Numeric dates are the most common error. 03/04/2026 means 3 April in the UK and 4 March in the US, so write the month name.

Abbreviations are ambiguous: 'St.' can be Street or Saint, and 'Dr.' can be Doctor or Drive. Write the full word when it matters, and preview any acronym that could be read either as letters or as a word.

  • UK order: '4 March 2026'. US order: 'March 4, 2026'. Match the order to your audience.

Accents and regional varieties

English varieties differ in vowels, rhythm and vocabulary, and every voice is labelled with its accent.

No voice is labelled Scottish, Welsh, Jamaican or other Caribbean English. For those audiences, choose the closest British or American voice and listen to a test paragraph before you publish.

Choosing between the English voices

The 11 American female Studio voices differ most in pace and intonation. Nicole is the slowest reader of all 75 voices measured (118 words per minute) and has the widest intonation range in the group (17.8 semitones), which suits calm, expressive narration. River reads fastest in the group at 228 words per minute with a steady 5.6-semitone range. For a lower voice, Alloy (146 Hz) and Kore (152 Hz) sit at the bottom of the group; Jessica (208 Hz) and Bella (203 Hz) sit at the top.

Among the 9 American male Studio voices, Onyx is the deepest at 86 Hz and Eric the highest at 156 Hz, as well as the fastest reader in the library (230 words per minute). On the British side, Lewis is the deepest voice of all 75 (85 Hz), Fable has the widest intonation range in the library (24.1 semitones), and George is the highest British male Studio voice at 140 Hz with an even 180 words per minute.

Global voices keep their natural pace, so choose them by accent first. For US audiences, Ava (201 Hz) and Andrew (112 Hz) are a clear female/male pair; Guy (155 Hz) is the highest American male Global voice and Eric (106 Hz) the lowest. For India, Neerja (258 Hz) sits far above Prabhat (121 Hz). For Nigeria, Ezinne (192 Hz) and Abeo (115 Hz) give the same female/male contrast. Maisie (British, 299 Hz) and Ana (American, 296 Hz) are the two highest-pitched voices, which fits their use for younger characters.

Common mistakes when turning English text into speech

  • Writing 'us' for the country: 'US' is the United States, while 'us' is a pronoun. Capitalise the country.
  • Dropping the comma in direct address: 'Let's eat Grandma' and 'Let's eat, Grandma' mean different things. Add the comma so the pause is in the right place.
  • Using all capitals for emphasis: a word in capitals may be read letter by letter. Use normal case and punctuation instead.
  • Mixing 'color' and 'colour' in one script: choose one spelling variety, because mixed spellings also make captions look wrong.

English voices compared — measured

Each voice read the same English text at normal speed. Lower pitch sounds deeper; a wider intonation range sounds livelier, a narrower one steadier.

VoiceGenderAccent PitchIntonation range Speaking rate
Alloy STUDIO Female American 146 Hz 6.5 st 219 wpm
Kore STUDIO Female American 152 Hz 8.7 st 204 wpm
Sky STUDIO Female American 153 Hz 9.9 st 201 wpm
Nova STUDIO Female American 157 Hz 8.9 st 222 wpm
Nicole STUDIO Female American 158 Hz 17.8 st 118 wpm
River STUDIO Female American 166 Hz 5.6 st 228 wpm
Emma GLOBAL Female American 168 Hz 13.8 st 193 wpm
Yan GLOBAL Female Hong Kong 173 Hz 10.1 st 162 wpm
Emma Multilingual GLOBAL Female American 173 Hz 12.6 st 184 wpm
Aoede STUDIO Female American 177 Hz 7.9 st 197 wpm
Emma STUDIO Female British 181 Hz 5.1 st 200 wpm
Jenny GLOBAL Female American 181 Hz 10.0 st 170 wpm
Molly GLOBAL Female New Zealand 182 Hz 12.3 st 150 wpm
Michelle GLOBAL Female American 184 Hz 7.3 st 167 wpm
Clara GLOBAL Female Canadian 184 Hz 9.4 st 164 wpm
Luna GLOBAL Female Singaporean 186 Hz 7.1 st 150 wpm
Emily GLOBAL Female Irish 189 Hz 12.4 st 148 wpm
Leah GLOBAL Female South African 190 Hz 6.1 st 156 wpm
Sarah STUDIO Female American 191 Hz 8.9 st 191 wpm
Ezinne GLOBAL Female Nigerian 192 Hz 6.7 st 164 wpm
Sonia GLOBAL Female British 193 Hz 11.2 st 171 wpm
Ava Multilingual GLOBAL Female American 194 Hz 9.3 st 187 wpm
Imani GLOBAL Female Tanzanian 196 Hz 8.6 st 158 wpm
Libby GLOBAL Female British 196 Hz 10.5 st 151 wpm
Heart STUDIO Female American 197 Hz 6.5 st 186 wpm
Lily STUDIO Female British 198 Hz 9.8 st 202 wpm
Asilia GLOBAL Female Kenyan 198 Hz 6.8 st 158 wpm
Isabella STUDIO Female British 199 Hz 5.0 st 203 wpm
Ava GLOBAL Female American 200 Hz 10.6 st 179 wpm
Natasha GLOBAL Female Australian 202 Hz 12.3 st 158 wpm
Rosa GLOBAL Female Philippine 202 Hz 7.1 st 157 wpm
Bella STUDIO Female American 203 Hz 6.4 st 182 wpm
Aria GLOBAL Female American 205 Hz 9.6 st 161 wpm
Alice STUDIO Female British 207 Hz 10.2 st 205 wpm
Jessica STUDIO Female American 208 Hz 9.6 st 223 wpm
Neerja GLOBAL Female Indian 258 Hz 13.7 st 148 wpm
Neerja (expressive) GLOBAL Female Indian 271 Hz 13.9 st 152 wpm
Ana GLOBAL Female American 296 Hz 6.9 st 144 wpm
Maisie GLOBAL Female British 299 Hz 5.8 st 153 wpm
Lewis STUDIO Male British 85 Hz 11.0 st 180 wpm
Onyx STUDIO Male American 86 Hz 7.3 st 222 wpm
Liam GLOBAL Male Canadian 98 Hz 14.2 st 176 wpm
William Multilingual GLOBAL Male Australian 102 Hz 12.2 st 184 wpm
Eric GLOBAL Male American 106 Hz 11.0 st 161 wpm
Echo STUDIO Male American 107 Hz 10.8 st 217 wpm
James GLOBAL Male Philippine 108 Hz 8.2 st 173 wpm
Puck STUDIO Male American 109 Hz 5.2 st 217 wpm
Christopher GLOBAL Male American 110 Hz 10.6 st 164 wpm
Andrew GLOBAL Male American 112 Hz 13.8 st 195 wpm
Fable STUDIO Male British 114 Hz 24.1 st 212 wpm
Chilemba GLOBAL Male Kenyan 114 Hz 4.9 st 176 wpm
Elimu GLOBAL Male Tanzanian 114 Hz 8.8 st 171 wpm
Abeo GLOBAL Male Nigerian 115 Hz 7.3 st 174 wpm
Adam STUDIO Male American 115 Hz 5.8 st 195 wpm
Andrew Multilingual GLOBAL Male American 115 Hz 12.7 st 181 wpm
Michael STUDIO Male American 116 Hz 7.6 st 171 wpm
Luke GLOBAL Male South African 118 Hz 4.8 st 187 wpm
Thomas GLOBAL Male British 119 Hz 11.2 st 168 wpm
Brian GLOBAL Male American 119 Hz 5.7 st 182 wpm
Brian Multilingual GLOBAL Male American 119 Hz 5.9 st 182 wpm
Wayne GLOBAL Male Singaporean 120 Hz 8.5 st 150 wpm
Prabhat GLOBAL Male Indian 121 Hz 14.1 st 141 wpm
Daniel STUDIO Male British 122 Hz 6.6 st 217 wpm
Steffan GLOBAL Male American 122 Hz 6.4 st 176 wpm
Mitchell GLOBAL Male New Zealand 122 Hz 12.9 st 159 wpm
Ryan GLOBAL Male British 124 Hz 14.8 st 167 wpm
Liam STUDIO Male American 130 Hz 12.9 st 219 wpm
Fenrir STUDIO Male American 136 Hz 8.7 st 201 wpm
Roger GLOBAL Male American 138 Hz 13.7 st 160 wpm
George STUDIO Male British 140 Hz 7.8 st 180 wpm
Santa STUDIO Male American 151 Hz 13.1 st 188 wpm
Connor GLOBAL Male Irish 151 Hz 15.9 st 167 wpm
Guy GLOBAL Male American 155 Hz 6.0 st 169 wpm
Eric STUDIO Male American 156 Hz 9.1 st 230 wpm
Sam GLOBAL Male Hong Kong 170 Hz 6.3 st 152 wpm

Measured by SpeakScribe in October 2026 from each voice's audio. Pitch is the median fundamental frequency; intonation range is the spread between the 10th and 90th percentile of pitch. Speaking rate is words per minute on a 59-word passage. st = semitones. Methodology · How SpeakScribe voices work

Which English voice for YouTube narration

A selection of the most-visited English voices on SpeakScribe, ordered by measured intonation range (how much the pitch moves while reading). Across all 75 measured English voices the median is 9.1 semitones and 16.0 characters a second.

  • Ryan 14.8 st · 15.8 chars/s

    British · Global

    +5.7 st vs the median: livelier delivery for stories, reviews and intros.

  • Emma 13.8 st · 17.5 chars/s

    American · Global

    +4.7 st vs the median: livelier delivery for stories, reviews and intros; reads 1.5 chars/s faster than the median, handy for Shorts.

  • Santa 13.1 st · 16.1 chars/s

    American · Studio

    +4.0 st vs the median: livelier delivery for stories, reviews and intros.

  • Andrew Multilingual 12.7 st · 16.6 chars/s

    American · Global

    +3.6 st vs the median: livelier delivery for stories, reviews and intros.

  • Sonia 11.2 st · 16.3 chars/s

    British · Global

    +2.1 st vs the median: livelier delivery for stories, reviews and intros.

  • Thomas 11.2 st · 15.9 chars/s

    British · Global

    +2.1 st vs the median: livelier delivery for stories, reviews and intros.

  • Lewis 11.0 st · 16.4 chars/s

    British · Studio

    +1.9 st vs the median: livelier delivery for stories, reviews and intros.

  • Ava 10.6 st · 16.9 chars/s

    American · Global

    +1.5 st vs the median: livelier delivery for stories, reviews and intros.

  • Jenny 10.0 st · 15.9 chars/s

    American · Global

    +0.9 st vs the median: a neutral default for explainers.

  • Aria 9.6 st · 15.7 chars/s

    American · Global

    +0.5 st vs the median: a neutral default for explainers.

  • Michelle 7.3 st · 15.6 chars/s

    American · Global

    -1.8 st vs the median: steadier delivery for tutorials, instructions and calm documentaries.

  • Brian 5.7 st · 15.7 chars/s

    American · Global

    -3.4 st vs the median: steadier delivery for tutorials, instructions and calm documentaries.

Same measurements as the table above (October 2026). "Why it fits" follows from the numbers: a range 1.5 semitones or more above the median reads as livelier, 1.5 or more below as steadier; pace is compared with the quarter of voices that read fastest and slowest. Making YouTube videos with SpeakScribe voices →

More for English creators

Frequently asked questions

Global: Libby, Maisie, Sonia, Ryan and Thomas. Studio (speed control, WAV): Alice, Emma, Isabella, Lily, Daniel, Fable, George and Lewis.
Yes. Neerja, an expressive version of Neerja, and Prabhat speak with an Indian English accent. All three are Global voices.
The multilingual Global voices: Ava, Emma, Andrew and Brian (American) and William (Australian). They keep the same voice when your script switches language.
No. The Studio Emma is British and the Global Emma is American, so check the accent label before you choose.
Molly (female) and Mitchell (male) use a New Zealand accent. Emily (female) and Connor (male) use an Irish accent.
Voices pronounce from the spelling, so preview the name and respell it in the script if it is read wrongly.
Yes. Under SpeakScribe's Terms (section 6), audio from the 28 English Studio voices may be used for any purpose, including paid advertising, broadcast and client work. The 47 Global voices may be used in your own content, including monetized videos on your channel; for paid ads, broadcast or client work use a Studio voice. No attribution is needed. Whether a channel earns money is decided by YouTube under its own content policies, which favour original videos.
A free account converts up to 5,000 characters per render, about 5 minutes of English speech at the median pace of 16.0 characters a second. Starter allows 30,000 characters per render (about 31 minutes) and the largest plan 150,000 (about 156 minutes), delivered as one file.
Yes, with Multi-voice: each line gets its own speaker and the result is one MP3 with every voice levelled to the same loudness. Free accounts can try 2 speakers (3 dialogues a month, up to 1,500 characters); paid plans allow 4 to 10 speakers.
Paid plans export SRT and VTT subtitle files with every voiceover, timed from the voice itself; in our test the average offset was 26–97 ms. Free accounts see a preview of the first lines.

Generate English voiceover audio free

Pick a voice above, paste your script, and export publish-ready audio in seconds.

Open Voice Studio