Actions6
Text-to-Dialogue V3
AI-generatedSummary
Convert a structured dialogue script into a multi-voice spoken audio dialogue using ElevenLabs V3 model.
Inputs
- modelDialogue — Select the ElevenLabs dialogue model (default is ElevenLabs V3).
- languageCode — Specify the dialogue language for generation; uses auto-detect if set to 'auto' (default).
- dialogue (required) — Define one or more dialogue lines as a fixed collection with each line specifying a voice from a provided set and the text to speak.
- replyUrl — Optional webhook URL for asynchronous task completion notification.
- replyRef — Optional custom reference string included in the webhook callback.
- waitForCompletion — Whether to wait and poll for the task's completion (default true).
Output shape
a JSON array with one element per input item, each containing the API response data for the created dialogue task and (if waitForCompletion is true) the finalized dialogue audio generation result or error details.
If 'waitForCompletion' is enabled (default), the node polls the Kie.ai API until the dialogue generation completes or times out (5 minutes). Otherwise, it returns immediately with the task creation response. The API response includes URLs to the generated audio and metadata for downstream use.
Examples
Example 1: Create a multi-voice dialogue audio from specified lines
Provide multiple dialogue lines specifying a voice and text each, choose language or leave as 'auto', and optionally set webhook parameters and waitForCompletion flag.