ElevenLabs

This page is auto-generated from model configurations. Last updated: 2026-08-18.

This reference lists all available ElevenLabs video generation models and their parameters. Use these parameter names when calling the Generation API.

• ElevenLabs Dubbing
• ElevenLabs Dubbing v2

---

ElevenLabs Dubbing

Automatically dub audio or video content into another language while preserving speaker voices.

Model ID: model_elevenlabs-dubbing

Capabilities: audio2audio, video2video

LLM Markdown: https://app.scenario.com/api/models/model_elevenlabs-dubbing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
file	file	Yes	-	-	-	-	The audio or video file to dub.
targetLang	string	Yes	en	-	-	en, es, fr, de, it, ja, ko, zh, ru, ar, hi, pt, nl, sv, da, no, fi, pl, tr, id, th, vi, ms, tl, ro, hu, cs, sk, uk, bg, hr	The target language for dubbing (ISO 639-1 code).
sourceLang	string	No	-	-	-	``, en, es, fr, de, it, ja, ko, zh, ru, ar, hi, pt, nl, sv, da, no, fi, pl, tr, id, th, vi, ms, tl, ro, hu, cs, sk, uk, bg, hr	The source language of the audio (ISO 639-1 code). Leave empty for auto-detection.
numSpeakers	number	No	0	0	10	-	Number of speakers in the audio. Set to 0 for automatic detection.
dropBackgroundAudio	boolean	No	false	-	-	-	Whether to remove background audio from the dubbed output.
disableVoiceCloning	boolean	No	false	-	-	-	Whether to disable voice cloning and use a generic voice instead.
highestResolution	boolean	No	false	-	-	-	Whether to return the dubbed video in the highest resolution available.

ElevenLabs Dubbing v2

Next-generation automatic dubbing with improved translation and voice quality. Preserve brand names and jargon with keyterms.

Model ID: model_elevenlabs-dubbing-v2

Capabilities: audio2audio, video2video

LLM Markdown: https://app.scenario.com/api/models/model_elevenlabs-dubbing-v2/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
file	file	Yes	-	-	-	-	The audio or video file to dub.
targetLang	string	Yes	en	-	-	en, es, fr, de, it, ja, ko, zh, ru, ar, hi, pt, nl, sv, da, no, fi, pl, tr, id, th, vi, ms, tl, ro, hu, cs, sk, uk, bg, hr	The target language for dubbing (ISO 639-1 / BCP-47 code).
sourceLang	string	No	auto	-	-	auto, en, es, fr, de, it, ja, ko, zh, ru, ar, hi, pt, nl, sv, da, no, fi, pl, tr, id, th, vi, ms, tl, ro, hu, cs, sk, uk, bg, hr	The source language of the audio (ISO 639-1 / BCP-47 code). Use auto for automatic detection.
keyterms	string_array	No	-	-	-	-	Terms to preserve verbatim across translation (names, brands, jargon). Max 1000 terms of up to 50 characters each.