Home › Prompts › ElevenLabs › Expressive narration with audio tags

Expressive narration with audio tags

A narration script that uses inline audio tags for emotion, pauses and reactions, the control method in Eleven v4.

ElevenLabsVoice & audioRuleStack original

Written for Eleven v4 (eleven_v4) · Updated 2026-10-16

Note: Review and test before use. Provided as is, without warranty. See Terms.

[calm] Welcome back to [show or product name]. [pause] Today we're looking at [topic]. [curious] Have you ever wondered why [hook question]? [short pause] Here's the surprising part. [excited] [key point]. [sighs] I know, I didn't believe it either. [warm] Let's dig in.

Replace everything in [square brackets] with your own details.

Settings & parameters

• API: model_id: "eleven_v4"; eleven_v4_turbo for real-time (~150 ms to first speech)
• SSML is disabled in v4; use bracket tags like [pause], [long pause], [whispers], [laughs]
• Use pronunciation dictionaries for names and technical terms

Variations

• Audiobook: fewer tags, [long pause] between paragraphs.
• Ad read: [energetic] at start, [confident] on the CTA.

Tips

• Tags go where the delivery should change; don't tag every sentence.
• Clone only your own voice or a voice you have written permission to use.