Eleven v3<\/strong> is the expressive one. It covers more than 70 languages, carries audio tags and multi-speaker dialogue, takes 5,000 characters per generation for about five minutes of speech, and is still marked experimental.<\/p>\n Eleven Multilingual v2<\/strong> is the stable, professional option. It covers 29 languages, takes 10,000 characters for about ten minutes in one pass, and is what ElevenLabs themselves recommend for content creation, audiobooks and video narration.<\/p>\n Both run at 3 credits per 1,000 characters, so the choice is about the read rather than the cost.<\/p>\n That surprises people. Eleven v3 is newer and more capable, but for a straight voiceover on a finished video, consistency across a long read matters more than dramatic range, and Multilingual v2 also gives you double the script length in one pass.<\/p>\n Before you write a single instruction, the voice is already responding to what your script says. ElevenLabs voices pick up emotional cues in the text and adapt delivery to both the sentence at hand and the wider context around it, which is what stops a line landing in the wrong tone when the subject changes.<\/p>\n That matters in practice, because a well-written script often needs no direction at all. Tags are for the moments where you want something the words alone would not produce.<\/p>\n Audio tags are what set Eleven v3 apart. Write a cue in square brackets, drop it inline in the script, and the delivery changes at exactly that point.<\/p>\n The tags group into three kinds:<\/p>\n Capital letters carry weight too, so a shouted line reads as And GOOOOAL!<\/strong> rather than leaning on a tag alone. Character colour comes from stacked cues like [laughs wickedly] and [evil laugh].<\/p>\n Longer tag lists circulate online, but they are community-collected and not all of them fire. Sticking to the documented set is the difference between a script that performs and one that reads your notes aloud.<\/p>\n Punctuation is performance direction. Commas and full stops create the pauses, so a run-on sentence gets read as a run-on sentence. Spell out anything unusual the way you want it said, including acronyms, product names and numbers, and respell a stubborn word phonetically if it keeps coming out wrong.<\/p>\n Give the model enough runway as well. A clipped fragment offers no context for setting tone, so a few full sentences almost always read better than one short line.<\/p>\n Eleven v3 supports natural multi-speaker dialogue. Label each speaker on its own line and let a single generation carry the whole exchange:<\/p>\n Speakers in one generation share context, so timing, interruptions and reactions all land naturally, and even overlapping speech survives. Generating each part separately and stitching the takes together loses precisely that, and the joins are audible.<\/p>\n Voices are grouped by the job they are built for, which is a faster way in than scrolling a list. Narration voices carry audiobooks and podcasts. Conversational voices suit informal, spoken-word scenarios. Character voices are built for cartoons and games. Social media voices are made to hold attention in short-form video, and advertisement voices aim at recall and action.<\/p>\nThe model reads the room, not just the words<\/span><\/h2>\n
Directing delivery with audio tags<\/span><\/h2>\n
[slowly] Back then... [chuckles] we had no phones.\r\n[whispers] Just dirt roads and [coughs] big dreams. [sad] Then it happened.<\/code><\/pre>\n\n
Writing a script the model reads well<\/span><\/h2>\n
Generating a two-person conversation<\/span><\/h2>\n
Mark\r\nHey Chris... Knock knock.\r\n\r\nChris\r\n[chuckles] I'm not doing this AGAIN!\r\n\r\nMark\r\n[laughing] Come on, PLEASE! I promise you'll love this one.<\/code><\/pre>\nChoosing a voice<\/span><\/h2>\n
What the finished audio sounds like<\/span><\/h2>\n
![\"\"](\"https:\/\/cdn-cms-uploads.picsart.com\/cms-uploads\/9b784b6b-6f78-4ee4-a748-f4ad781bfd34.svg\")
\n