Text to MP3 converter

Turn any text into an MP3 with a natural AI voice. Pick the bitrate, place your pauses, and download the file straight from your browser.

0 / 5,000 characters0 words≈ 0:00 spoken

Good for explainers, tutorials.

Delivery

Your audio appears here with a player and MP3 download. No sign-up, no watermark.

How big will my MP3 be?

An MP3’s size depends only on its bitrate and its length — not on the words. Bitrate is how many kilobits of data each second of audio gets. Drag the sliders to see the trade-off.

Speech is forgiving: a single voice occupies a narrow band of frequencies, so a low bitrate keeps almost all of it. Music, with cymbals and many instruments at once, needs far more.

Formula: size in MB ≈ kbps × seconds ÷ 8 ÷ 1000.

2.88 MB

Standard; accepted everywhere

Bitrate1 min10 minUse it for
32 kbps0.24 MB2.4 MBPhone-call quality; noticeable swirl on "s" sounds
64 kbps0.48 MB4.8 MBClean for a single voice; ideal for podcasts and e-learning
96 kbps0.72 MB7.2 MBIndistinguishable from 128 for most listeners
128 kbps0.96 MB9.6 MBStandard; accepted everywhere
192 kbps1.44 MB14.4 MBMusic-grade; no gain for speech

Getting a clean MP3 on the first try

  1. Write numbers the way they should sound. “2025” can be “twenty twenty-five” or “two thousand twenty-five”. Spell it out if it matters.
  2. Break long sentences. Anything over about 25 words is hard to follow by ear, no matter how good the voice is.
  3. Add silence where the edit needs it. A [pause 1s] at a scene change gives you room to cut in your editor.
  4. Check the length first. The counter under the text box estimates the spoken time; the words-to-minutes calculator explains the maths.

Need the whole of a document? The PDF to audio tool pulls out the text page by page.

Questions people ask

How do I convert text to MP3 for free?

Paste your text into the box, choose a voice and bitrate, press Generate speech, then Download MP3. The MP3 is encoded in your browser, so the download is instant once the audio is rendered. No sign-up is needed.

What bitrate should I use for a speech MP3?

For spoken word, 64 kbps mono already sounds clean and keeps files small; 96–128 kbps is a safe standard for video editors and podcast hosts. Above 128 kbps there is no audible improvement for a single voice.

Why are the files mono?

A single voice has no stereo information, so a stereo file would just double the size with two identical channels. Every editor and player handles mono MP3 normally.

Can I get a WAV file instead?

Yes. Next to Download MP3 there is a WAV button for uncompressed 24 kHz, 16-bit audio, which some video editors and broadcast workflows prefer.

Is there a length limit?

Each render takes up to 5,000 characters, which is roughly five to six minutes of speech. Split longer texts into chapters and render them one after another.

More from the studio