Unifically LogoUnificAlly
Model logo

ElevenLabs Dialogue API

ElevenLabs Multi-Voice Dialogue for conversations with multiple speakers

Add Speaker 3
Add speaker 3 to the dialogue
Output

Your generated audio will appear here

Features

What ElevenLabs Dialogue API offers

Structured dialogue array built from up to ten speakers in the playground UI
Two speakers always available, speakers three through ten unlocked with toggles
Per line voice id per speaker from the ElevenLabs voice catalog
language_code select including auto detect and many ISO codes
stability slider from 0 to 1 for delivery consistency
Dedicated text to dialogue generate and status endpoints on Unifically
Output is stitched conversational audio instead of a single monologue
Listed at $0.000184 per character for ElevenLabs Dialogue on Unifically

Use cases

Built for

Primary

Scripted podcasts with alternating hosts and distinct timbres

#2

Audiobook scenes with several cast voices in one API call

#3

Training simulators with role play lines and fixed casting

#4

Game barks when dialogue is short and turn based

#5

Product walkthroughs that sound like a chat instead of one narrator

#6

Language learning listens with per speaker clarity control via stability

FAQ

About ElevenLabs Dialogue API

It builds an array of { text, voice } turns. Each speaker uses an ElevenLabs voice id. The service renders one combined audio file for the conversation.

You fill Speaker 1 and Speaker 2 at minimum. Optional speakers three through ten appear when you enable their toggles, each with voice and text fields.

No. Dialogue uses its own integration path. You set languages and stability in the dialogue form rather than the single speaker TTS model list.

ElevenLabs Dialogue is priced at $0.000184 per character in published Unifically pricing.