What is Eleven v3?

Eleven v3 is an emotionally rich, expressive Text to Speech model. It produces natural, life-like speech with high emotional range and contextual understanding across 70+ languages.

Eleven v3 offers:

• Support for audio tags
  • emotions: [sad] [angry] [happily]
  • delivery direction: [whispers] [shouts]
  • non-verbal reactions: [laughs] [clears throat] [sighs]
• Dialogue mode for natural-sounding audio with multiple speakers
• Support for 70+ languages

This model works well for character discussions, audiobook narration, and emotional dialogue.

You can generate using v3 via API using our Create speech and Stream speech endpoints by specifying model ID eleven_v3.

You can also use our Create dialogue and Stream dialogue endpoints to create a natural sounding dialogue with multiple speakers.

Visit the following resources for more information:

• Models
• Prompting guide