Arabic AI Voice

Maryam — free Yemeni Arabic text to speech

Maryam is a free female Yemeni Arabic AI voice — a Microsoft neural voice. Type your text below to hear it read aloud, then download the audio. No account needed.

Female Yemeni accent Global voice Free

Make Maryam say your words

Voice details

Language
Arabic
Accent
Yemeni
Gender
Female
Type
Global · Microsoft neural
Download
MP3
Speed
Natural pace
Voice ID
ar-YE-MaryamNeural
Price
Free

How Maryam sounds — measured

Median pitch

234 Hz

The 4th highest of 16 female Arabic voices

Intonation range

11.4 semitones

Close to typical for its group

Tone (spectral centroid)

1,502 Hz

Balanced tone for its group

Speaking rate

9.3 characters/s

In the middle of 32 Arabic voices on the same passage

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

How long your audio will be at 9.3 characters/s

1,000 characters
≈ 1 min 47 s
5,000 characters (free limit per render)
≈ 9 min
  • ↔Compared with Amina, Maryam has a similar pitch (234 vs 235 Hz) and faster delivery (9.3 vs 8.6 characters/s). Listen to Amina →
  • ↔Compared with Mouna, Maryam has a similar pitch (234 vs 237 Hz). Listen to Mouna →

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

What Maryam fits best

  • Tutorials, kids' content and friendly explainers

    At 234 Hz it sits above 12 of the 16 female Arabic voices, which sounds bright and approachable.

Use Maryam in a conversation

With Multi-voice, Maryam can read one character while Shakir (a male Arabic 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 Maryam →

Formats, limits and help

Maryam: quick answers

Measured from its audio, Maryam has a median pitch 234 Hz (the 4th highest of 16 female Arabic voices); intonation range 11.4 semitones (close to typical for its group); tone (spectral centroid) 1,502 Hz (balanced tone for its group).
About 1 min 47 s. Maryam reads about 9.3 characters a second, spaces included (measured on its sample passage), so the free limit of 5,000 characters per render is about 9 minutes of audio. Numbers, names and long pauses make it longer.