Short answer: to get shouting, screaming or yelling text to speech, put your text inside a <loud>…</loud> tag and generate it with Grok text to speech. The box above already does this: Shout all text wraps everything you type, so you can paste a line, pick one of 28 voices and press Generate. Turn the button off to shout only part of a script. Trying it needs no account.
How to make a shouting voice
- Paste or type your text in the box. The sample line is already shouted; replace it with your own.
- Keep Shout all text on to shout everything. The box shows the tag around your text, so you always see what gets sent.
- Pick a voice. All 28 voices accept the loud tag; the clips above use Eve.
- Press Generate and listen. Signed in, you can download the result as an MP3.
To shout just one sentence, turn Shout all text off, select the sentence, open More tags under Add expression and pick <loud>. That wraps only your selection:
I told you twice. [pause] <loud>Get out of the water!</loud>
What the loud tag does
<loud> is one of 26 speech tags in xAI's text to speech docs, listed under volume and intensity. It is a wrapping tag: it changes how the words between <loud> and </loud> are spoken, and the tags themselves are not read out.
What it changes is the delivery, not the volume knob. In our two pre-recorded clips of the same line in the same voice, the shouted one came out the same length (5.5 seconds) at the same average level, but with a median pitch about 30% higher and a brighter tone. Expect the same voice raised and pushed, not a louder file; turn up the volume on your side if you need both.
Ideas to try
These are suggestions, not tests we ran for each use:
- Warnings and commands: a short shouted line after a normal one, with a
[pause]before it. - Sports and crowd scenes: wrap the call in
<loud>and let<build-intensity>ramp up the last phrase. - Arguments in dialogue: shout one character's reply while the other keeps a normal read;
[exhale]after the shout reads as frustration. - Announcements and ads: shout the headline, then switch back to a normal read for the details.
Tips for a better shout
- Shout whole sentences. A wrapped phrase reads more naturally than a single shouted word.
- Add punctuation. Exclamation marks and short sentences give the shout its rhythm.
- Stack tags for more intensity.
<loud><emphasis>Now!</emphasis></loud>stresses a word inside a shout;<build-intensity>rises over a phrase. - Try two or three voices. The same text can sound quite different from voice to voice; the voices page has every voice reading one sentence.
- Go the other way. The whisper text to speech page does a whole script in a whisper, and the text to speech with emotion page combines tags into one-click moods. The full list is in the speech tags guide.
Limits, price and privacy
Signed out, you get 3 previews a day of up to 200 characters, played on the page; a free account adds MP3 download, and a Google account raises the limit to 1,000 characters per clip. The tag characters count toward the limit. Your text goes to xAI's model through our Cloudflare function to make the audio and is not stored.
If you build your own app, the same model costs $15 per million characters through xAI's API; see the pricing calculator. There is no separate price for shouting; xAI bills text to speech per character.
Last updated: