Eleven v3 Audio Tags: Precision delivery control for AI speech

Great speech isn’t just about what’s said — it’s how it’s said. With Eleven v3 Audio Tags, you gain fine-grained control over timing, rhythm, and emphasis, allowing you to shape the pacing of a line with precision.

Using tags like [pause], [rushed], [stammers], or [drawn out], you can adjust how each sentence lands — not just emotionally, but rhythmically. That control turns flat delivery into performance.

What is delivery control in AI speech?

Delivery control is the ability to direct the flow of speech — how quickly it moves, where it pauses, when it emphasizes. It’s what makes a line feel dramatic, casual, tense, or comedic.

Con Eleven v3, la entrega no está limitada al ritmo predeterminado. Puedes ralentizar para crear suspense, acelerar para dar urgencia o añadir ritmo para el humor, directamente desde el guion.

Example:  "Okay, so like I finally beat level 42 of that game I said I’d quit like... a month ago. [laughs] And then the final boss... was just... [giggle] a bunny rabbit. [big laugh] I couldn’t do it. It was too cute."

Tags here shape the tempo and timing — and that’s what makes the line land.

Controlling timing, pacing, and presence

Tags give you access to the subtle cues humans use to pace speech naturally:

• Pauses & breaks: [pause], [breathes], [continues after a beat]
• Speed cues: [rushed], [slows down], [deliberate], [rapid-fire]
• Hesitation & rhythm: [stammers], [drawn out], [repeats], [timidly]
• Emphasis: [emphasized], [stress on next word], [understated]

Example: "[drawn out] Sooooo... you're saying... [suspicious tone] you didn't eat the last slice?"

These tags give you complete control over how a voice feels in motion.

Pacing for tone and meaning

Changing how a line is delivered changes how it's interpreted.

Compare:

• I’m fine.
• [flatly] I’m fine.
• [quietly, after a pause] I’m... fine.
• [angrily, fed up] I'm FINE!
• [questioning]Are you [pause] sure you're fine?
• I’m fine. [pause] really!

Same words. Different meaning. With delivery control, tone emerges not from word choice, but from timing and intent.

Tag combinations that define the moment

You can layer delivery-focused tags with emotional or character cues to shape entire scenes.

Example: [hesitant][nervous] I... I’m not sure this is going to work. [gulps] But let’s try anyway.

Or: [whispering][pause] Did you hear that? [rushed] Hide! Now!

It’s this mix of rhythm and reaction that makes performances feel believable.

Directing tempo, not just text

Eleven v3 turns the script into a score — and delivery control is how you conduct it. Whether you’re scripting tutorials, monologues, or punchlines, Audio Tags let you manage delivery with frame-by-frame precision.

For creators, this means complete command over how a line unfolds. You’re not just writing what happens. You’re setting its tempo.

Selecting the right voice

Professional Voice Clones (PVCs) are currently not fully optimized for Eleven v3, resulting in potentially lower clone quality compared to earlier models. During this research preview stage it would be best to find an Instant Voice Clone (IVC) or designed voice for your project if you need to use v3 features. PVC optimization for v3 is coming in the near future.