Spanish AI Voice

Teresa — free Equatorial Guinean Spanish text to speech

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

Female Equatorial Guinean accent Global voice Free

Make Teresa say your words

Voice details

Language
Spanish
Accent
Equatorial Guinean
Gender
Female
Type
Global · Microsoft neural
Download
MP3
Speed
Natural pace
Voice ID
es-GQ-TeresaNeural
Price
Free

How Teresa sounds — measured

Median pitch

202 Hz

In the middle of 24 female Spanish voices

Intonation range

5.9 semitones

Close to typical for its group

Tone (spectral centroid)

2,580 Hz

Balanced tone for its group

Speaking rate

16.8 characters/s

The 8th fastest of 48 Spanish voices on the same passage

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

How long your audio will be at 16.8 characters/s

1,000 characters
≈ 1 min
5,000 characters (free limit per render)
≈ 5 min
  • ↔Compared with Marta, Teresa has a similar pitch (202 vs 200 Hz). Listen to Marta →
  • ↔Compared with Ramona, Teresa has a similar pitch (202 vs 199 Hz) and faster delivery (16.8 vs 13.4 characters/s). Listen to Ramona →

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

What Teresa fits best

  • Fast-paced social video

    At 16.8 characters a second it fits more text into a short clip.

Use Teresa in a conversation

With Multi-voice, Teresa 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 Teresa →

Formats, limits and help

Teresa: quick answers

Measured from its audio, Teresa has a median pitch 202 Hz (in the middle of 24 female Spanish voices); intonation range 5.9 semitones (close to typical for its group); tone (spectral centroid) 2,580 Hz (balanced tone for its group).
About 1 min. Teresa reads about 16.8 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.