ElevenLabs v4

Overview

What is ElevenLabs v4?

Eleven v4 is ElevenLabs’ latest text-to-speech model (September 2026). It generates expressive speech, with audio tags to direct delivery, stability and similarity settings, and IPA pronunciation.

It is Havincy’s default voice: voiceovers, narration, dialogue, in many languages.

Key strengths

• Natural
• Expressive
• Latest generation

Specs

ElevenLabs v4: specifications

Publisher

ElevenLabs

Generation modes

text → speech

Audio

Sound generated with the video

Available since

September 28, 2026

License

Commercial use allowed

Cost in Havincy

From 23 credits

Specs taken from the publisher’s public model page. See the documentation on fal.ai

Use cases

What you can create with ElevenLabs v4

Prompt examples

Prompts to try with ElevenLabs v4

Paste an example into Havincy, then adapt the subject, style and format to your project.

• 01

  Warm 20-second voiceover presenting our new collection.

• 02

  Read this text with enthusiasm, then slow down on the last sentence.

• 03

  Dialogue between a customer and a salesperson, natural tone.

Use cases

Compatible skills

Use this model with the following Havincy skills.

How it works

How to create with this model

1. Describe the desired result in a Havincy conversation.
2. Add a reference when the style, product, or character needs to be preserved.
3. Generate, then ask for a variation or improvement without starting over.

FAQ

Frequently asked questions about ElevenLabs v4