Skip to main content
POST
Eleven v3 Dialogue
eleven-v3-dialogue turns a list of lines, each with its own voice, into one audio file of a conversation, using ElevenLabs Eleven v3. Confirm live rates on the SnapGen models page. Failed requests are not charged.
string
required
Set to eleven-v3-dialogue.
object[]
required
1 to 50 lines in speaking order, each an object with text and voice (a voice ID or first name from the voice list). The text of all lines totals at most 2,000 characters, and a dialogue uses at most 10 different voices.
string
default:"mp3"
mp3, opus, pcm, or wav. See Output formats.
string
An ISO 639 language code of two or three lowercase letters, such as en or de. The provider rejects a code the model doesn’t support.
number
From 0 to 1. Lower values give a broader emotional range; higher values sound more consistent.
integer
From 0 to 4294967295. Makes repeated requests more repeatable, without guaranteeing identical audio.

Request

The response body is the audio file, with a Content-Type that matches response_format.

Price examples

Synchronous audio endpoints reject Idempotency-Key. If a request times out, check your Console request logs before you retry. See Text to dialogue for every field, the response, and errors.