What are Eleven v3 Audio Tags — and why they matter

With the release of Eleven v3, l'audio prompting est devenu une compétence essentielle. Au lieu de taper ou coller les mots que vous voulez que la voix IA dise, vous pouvez maintenant utiliser une nouvelle capacité — Audio Tags — to control everything from emotion to delivery.

Eleven v3 is an alpha release research preview du nouveau modèle. Cela nécessite plus d'ingénierie de promptque les modèles précédents — mais les générations sont époustouflantes.

ElevenLabs Audio Tags are words wrapped in square brackets that the new Eleven v3 model can interpret and use to direct the audible action. They can be anything from [excited], [whispers], and [sighs] through to [gunshot], [clapping] and [explosion].

Audio Tags let you shape how AI voices sound, including nonverbal cues like tone, pauses, and pacing. Whether you're building immersive audiobooks, interactive characters, or dialogue-driven media, these simple script-level tools give you precise control over emotion and delivery.

Directing performance with Audio Tags

You can place Audio Tags anywhere in your script to shape delivery in real time. You can also use combinations of tags within a script or even a sentence. Tags fall into core categories:

Emotions

These tags can help you set the emotional tone of the voice — whether it's somber, intense, or upbeat. For example you could use one or a combination of [sad], [angry], [happily] and [sorrowful].

Delivery direction

These are more about the tone and performance. You can use these tags to adjust volume and energy for scenes that need restraint or force. Examples include: [whispers], [shouts] and even [x accent].

Human reactions

True natural speech includes reactions. For example, you can use this to add realism by embedding natural, unscripted moments into speech. For example: [laughs], [clears throat] and [sighs].

Built on a more expressive model

Underpinning these features is the new architecture behind v3. The model understands text context at a deeper level, which means it can follow emotional cues, tone shifts, and speaker transitions more naturally. Combined with Audio Tags, this unlocks greater expressiveness than was previously possible in TTS.

You can now also create multi-speaker dialogues that feel spontaneous — handling interruptions, shifting moods, and conversational nuance with minimal prompting.

Available now

Eleven v3 is available in the ElevenLAbs UI, and we’re offering 80% off until the end of June. Public API for Eleven v3 (alpha) is coming soon. For early access, please contact sales. Whether you’re experimenting or deploying at scale, now’s the time to explore what’s possible.