English AI Voice

Michael — free American English text to speech

Michael is a free male 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.

Male American accent Studio voice Free

Make Michael say your words

Voice details

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

How Michael sounds — measured

Median pitch

116 Hz

In the middle of 18 male American English voices

Intonation range

7.6 semitones

Close to typical for its group

Tone (spectral centroid)

2,465 Hz

Brighter, crisper tone than most of its group

Speaking rate

171 words/min

In the middle of 75 English voices measured

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

How long your audio will be at 15.1 characters/s

1,000 characters
≈ 1 min 6 s
5,000 characters (free limit per render)
≈ 6 min
  • ↔Compared with Andrew Multilingual, Michael has a similar pitch (116 vs 115 Hz), steadier intonation (7.6 vs 12.7 semitones) and a brighter tone. Listen to Andrew Multilingual →
  • ↔Compared with Adam, Michael has a similar pitch (116 vs 115 Hz), a brighter tone and slower delivery (171 vs 195 words/min). Listen to Adam →

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

Use Michael in a conversation

With Multi-voice, Michael can read one character while Alloy (a female 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 Michael →

Formats, limits and help

Michael: quick answers

Measured from its audio, Michael has a median pitch 116 Hz (in the middle of 18 male American English voices); intonation range 7.6 semitones (close to typical for its group); tone (spectral centroid) 2,465 Hz (brighter, crisper tone than most of its group).
About 1 min 6 s. Michael reads about 15.1 characters a second, spaces included (measured on its sample passage), so the free limit of 5,000 characters per render is about 6 minutes of audio. Numbers, names and long pauses make it longer.