Eleven v3

by ElevenLabs June 8, 2025

Eleven v3 is a premium text to speech model for production audio. It supports 70+ languages with studio grade quality and precise expressive control using inline audio tags. Ideal for narration, podcasts, dialogue, audiobooks, and game voiceover where stable prosody matters.

This model is deprecated and will be deactivated on June 18, 2026.

Directing voice with audio tags
How to direct vocal delivery in Eleven v3 with inline audio tags. The tags carry the emotion, sound effects, and multi-speaker turn-taking that plain text alone cannot.