Eleven v3 (Alpha) offers Dialogue mode, allowing you to generate dynamic multi-speaker conversations with natural pacing, that handle interruptions, shifts in tone, and emotional cues based on conversational context.
Dialogue mode is available when you use multiple speakers via the website.
We’ve also created a new Text to Dialogue API endpoint for generating multi-speaker interactions. For more information, see our API documentation.
During June, we’re offering an 80% discount on generations via the website for self-serve users. Generating via API is not yet publicly available. For early access, please contact sales.
Visit the following resources for more information: