English AI Voice

Sarah — free American English text to speech

Sarah is a free female American English AI voice — a Studio voice that runs on SpeakScribe's own servers, with adjustable speed. Type your text below to hear it read aloud, then download the audio. No account needed.

Female American accent Studio voice Free

Make Sarah say your words

Voice details

Language
English
Accent
American
Gender
Female
Type
Studio · Kokoro
Download
WAV
Speed
Adjustable, 0.5×–2×
Voice ID
af_sarah
Price
Free

How Sarah sounds — measured

Median pitch

191 Hz

In the middle of 19 female American English voices

Intonation range

8.9 semitones

Close to typical for its group

Tone (spectral centroid)

2,210 Hz

Brighter, crisper tone than most of its group

Speaking rate

191 words/min

The 23rd fastest of 75 English voices measured

Pitch across the sample passage dashed line = Sarah’s median

How long your audio will be at 17.5 characters/s

1,000 characters
≈ 57 s
5,000 characters (free limit per render)
≈ 5 min

Measured by SpeakScribe, October 2026 · How we measure · Every English voice side by side

What Sarah fits best

  • Fast-paced social video

    At 191 words/min it fits more words into a short clip.

Use Sarah in a conversation

With Multi-voice, Sarah can read one character while Adam (a male English voice) reads another — the whole dialogue comes back as one MP3 with even volume between speakers. A free account can make 3 two-speaker dialogues a month; paid plans allow up to 4 speakers on Starter.

Try a dialogue with Sarah →

Formats, limits and help

Sarah: quick answers

Measured from its audio, Sarah has a median pitch 191 Hz (in the middle of 19 female American English voices); intonation range 8.9 semitones (close to typical for its group); tone (spectral centroid) 2,210 Hz (brighter, crisper tone than most of its group).
About 57 s. Sarah reads about 17.5 characters a second, spaces included (measured on its sample passage), so the free limit of 5,000 characters per render is about 5 minutes of audio. Numbers, names and long pauses make it longer.