Text to Speech Guide: Multi-Speaker Dialogue with V3

Our new Dialogue V3 model transforms how you create spoken content. With support for multiple speakers, natural conversation flow, and over 100 unique voices, you can produce professional-quality audio content in minutes.

V3 vs V2: What's Different?

Feature	Turbo V2.5	Dialogue V3
Speakers	Single voice	Up to 10 speakers
Voices	39 voices	100+ voices
Credits	1 per generation	2 per 1000 characters
Controls	Speed, stability, similarity	Stability, language
Best for	Narration, single voice	Dialogue, podcasts, stories

Creating Multi-Speaker Dialogue

1. Select the V3 model — Open the Model selector in the settings panel
2. Add speakers — Click "Add Speaker" to create dialogue entries
3. Assign voices — Click the voice badge on each block to pick a unique voice
4. Write dialogue — Enter text for each speaker
5. Generate — Hit generate and listen to natural conversation

Voice Categories

V3 voices are organized into categories to help you find the perfect match:

• Conversational — Natural, everyday speaking voices
• Narration — Professional audiobook and storytelling voices
• Characters — Unique character voices for games and animation
• Social Media — Energetic voices for content creation
• Educational — Clear, professional teaching voices
• Entertainment — Radio, podcast, and media voices

Tips for Best Results

• Vary your voices — Use contrasting voices for different speakers
• Keep it natural — Write dialogue as people actually speak
• Use audio tags — Add [laughs], [whispers], or [excitedly] for expression
• Preview first — Listen to voice previews before selecting

Start creating with Dialogue V3 today!