Spanish AI Voice

Marcelo — free Bolivian Spanish text to speech

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

Male Bolivian accent Global voice Free

Make Marcelo say your words

Voice details

Language
Spanish
Accent
Bolivian
Gender
Male
Type
Global · Microsoft neural
Download
MP3
Speed
Natural pace
Voice ID
es-BO-MarceloNeural
Price
Free

How Marcelo sounds — measured

Median pitch

119 Hz

In the middle of 24 male Spanish voices

Intonation range

4.8 semitones

Close to typical for its group

Tone (spectral centroid)

2,584 Hz

Balanced tone for its group

Speaking rate

15.8 characters/s

In the middle of 48 Spanish voices on the same passage

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

How long your audio will be at 15.8 characters/s

1,000 characters
≈ 1 min 3 s
5,000 characters (free limit per render)
≈ 5 min
  • ↔Compared with Rodrigo, Marcelo has a similar pitch (119 vs 119 Hz). Listen to Rodrigo →
  • ↔Compared with Alex, Marcelo has a similar pitch (119 vs 120 Hz) and faster delivery (15.8 vs 13.9 characters/s). Listen to Alex →

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

Use Marcelo in a conversation

With Multi-voice, Marcelo can read one character while Ximena (a female 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 Marcelo →

Formats, limits and help

Marcelo: quick answers

Measured from its audio, Marcelo has a median pitch 119 Hz (in the middle of 24 male Spanish voices); intonation range 4.8 semitones (close to typical for its group); tone (spectral centroid) 2,584 Hz (balanced tone for its group).
About 1 min 3 s. Marcelo reads about 15.8 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.