Spanish AI Voice

Marta — free Guatemalan Spanish text to speech

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

Female Guatemalan accent Global voice Free

Make Marta say your words

Voice details

Language
Spanish
Accent
Guatemalan
Gender
Female
Type
Global · Microsoft neural
Download
MP3
Speed
Natural pace
Voice ID
es-GT-MartaNeural
Price
Free

How Marta sounds — measured

Median pitch

200 Hz

In the middle of 24 female Spanish voices

Intonation range

7.2 semitones

Close to typical for its group

Tone (spectral centroid)

2,340 Hz

Balanced tone for its group

Speaking rate

16.4 characters/s

The 13th fastest of 48 Spanish voices on the same passage

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

How long your audio will be at 16.4 characters/s

1,000 characters
≈ 1 min 1 s
5,000 characters (free limit per render)
≈ 5 min
  • ↔Compared with Ramona, Marta has a similar pitch (200 vs 199 Hz) and faster delivery (16.4 vs 13.4 characters/s). Listen to Ramona →
  • ↔Compared with Teresa, Marta has a similar pitch (200 vs 202 Hz). Listen to Teresa →

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

What Marta fits best

  • Fast-paced social video

    At 16.4 characters a second it fits more text into a short clip.

Use Marta in a conversation

With Multi-voice, Marta can read one character while Alvaro (a male Spanish 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 Marta →

Formats, limits and help

Marta: quick answers

Measured from its audio, Marta has a median pitch 200 Hz (in the middle of 24 female Spanish voices); intonation range 7.2 semitones (close to typical for its group); tone (spectral centroid) 2,340 Hz (balanced tone for its group).
About 1 min 1 s. Marta reads about 16.4 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.