ElevenLabs

This page is auto-generated from model configurations. Last updated: 2026-06-03.

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

• ElevenLabs Multilingual v2
• ElevenLabs Music
• ElevenLabs Music Advanced
• ElevenLabs Sound Effects v2
• ElevenLabs Turbo v2.5
• ElevenLabs v3

---

ElevenLabs Multilingual v2

Life-like, emotionally rich text-to-speech model supporting 29 languages.

Model ID: model_elevenlabs-multilingual-v2

Capabilities: txt2audio

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

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
text	string	Yes	-	-	-	-	The text to convert to speech
voiceId	model	No	-	-	-	-	Your cloned ElevenLabs voice model
publicVoice	string	No	Adam	-	-	Adam, Alice, Bella, Bill, Brian, Callum, Charlie, Chris, Daniel, Eric, George, Harry, Jessica, Laura, Liam, Lily, Matilda, River, Roger, Sarah, Will	Select a pre-built ElevenLabs public voice. Ignored if the input Voice is set.
stability	number	No	0.5	0	1	-	Voice stability
similarityBoost	number	No	0.5	0	1	-	Similarity boost
styleExaggeration	number	No	0	0	1	-	Style exaggeration
speed	number	No	1	0.7	1.2	-	Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality.
languageCode	string	No	-	-	-	“, en, ca, es, fr, de, it, ja, ko, zh, ru, ar, hi, bn, pa, ta, te, mr, ur, fa, tr, nl, sv, da, no, fi, el, ro, hu, cs, sk, sl, pt, id, th, vi, ms, tl, yo, ig, ha, am, az, be, bg, hr	Language code (ISO 639-1) used to enforce a language for the model.
outputFormat	string	No	mp3_44100_128	-	-	mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192	Output audio format.
seed	number	No	-	-	-	-	Seed for deterministic output

ElevenLabs Music

AI music generation from text descriptions.

Model ID: model_elevenlabs-music

Capabilities: txt2audio

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

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
prompt	string	Yes	-	-	-	-	A textual description of the music to generate.
musicLengthMs	number	No	30000	3000	180000	-	Duration of the music in milliseconds.
forceInstrumental	boolean	No	false	-	-	-	Whether to generate instrumental music without vocals.
outputFormat	string	No	mp3_44100_128	-	-	mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192	Output audio format.
seed	number	No	-	-	-	-	Seed for deterministic output

ElevenLabs Music Advanced

Advanced AI music generation with structured composition plans, section-by-section control, and lyrics.

Model ID: model_elevenlabs-music-advanced

Capabilities: txt2audio

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

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
positiveGlobalStyles	string_array	Yes	pop	-	-	-	Global styles to apply to the full song (e.g. ‘jazz’, ‘120 BPM’).
negativeGlobalStyles	string_array	No	-	-	-	-	Global styles to exclude from the full song.
sections	inputs_array	Yes	-	-	-	-	Ordered song sections defining the composition structure.
outputFormat	string	No	mp3_44100_128	-	-	mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192	Output audio format.
seed	number	No	-	-	-	-	Seed for deterministic output

ElevenLabs Sound Effects v2

Professional sound effects generation for audio production and content creation.

Model ID: model_elevenlabs-sound-effects-v2

Capabilities: txt2audio

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

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
text	string	Yes	-	-	-	-	A textual description of the sound effect to generate.
durationSeconds	number	No	5	0.5	30	-	Duration in seconds (0.5-30). If not set, optimal duration will be determined from prompt.
promptInfluence	number	No	0.3	0	1	-	How closely to follow the sound description. Higher values mean less variation.
loop	boolean	No	false	-	-	-	Whether to loop the sound effect.
outputFormat	string	No	mp3_44100_128	-	-	mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192	Output audio format.

ElevenLabs Turbo v2.5

High-quality, low-latency text-to-speech model in multiple languages.

Model ID: model_elevenlabs-turbo-v2-5

Capabilities: txt2audio

LLM Markdown: https://app.scenario.com/api/models/model_elevenlabs-turbo-v2-5/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
text	string	Yes	-	-	-	-	The text to convert to speech
voiceId	model	No	-	-	-	-	Your cloned ElevenLabs voice model
publicVoice	string	No	Adam	-	-	Adam, Alice, Bella, Bill, Brian, Callum, Charlie, Chris, Daniel, Eric, George, Harry, Jessica, Laura, Liam, Lily, Matilda, River, Roger, Sarah, Will	Select a pre-built ElevenLabs public voice. Ignored if the input Voice is set.
stability	number	No	0.5	0	1	-	Voice stability
similarityBoost	number	No	0.5	0	1	-	Similarity boost
styleExaggeration	number	No	0	0	1	-	Style exaggeration
speed	number	No	1	0.7	1.2	-	Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality.
languageCode	string	No	-	-	-	“, en, ca, es, fr, de, it, ja, ko, zh, ru, ar, hi, bn, pa, ta, te, mr, ur, fa, tr, nl, sv, da, no, fi, el, ro, hu, cs, sk, sl, pt, id, th, vi, ms, tl, yo, ig, ha, am, az, be, bg, hr	Language code (ISO 639-1) used to enforce a language for the model.
outputFormat	string	No	mp3_44100_128	-	-	mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192	Output audio format.
seed	number	No	-	-	-	-	Seed for deterministic output

ElevenLabs v3

Next-generation text-to-speech model with advanced voice synthesis and enhanced naturalness.

Model ID: model_elevenlabs-tts-v3

Capabilities: txt2audio

LLM Markdown: https://app.scenario.com/api/models/model_elevenlabs-tts-v3/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
text	string	Yes	-	-	-	-	The words that will be spoken aloud in the generated audio.
voiceId	model	No	-	-	-	-	A custom voice you cloned or trained to speak the text.
publicVoice	string	No	Adam	-	-	Adam, Alice, Bella, Bill, Brian, Callum, Charlie, Chris, Daniel, Eric, George, Harry, Jessica, Laura, Liam, Lily, Matilda, River, Roger, Sarah, Will	A ready-made ElevenLabs voice, used only when no custom Voice is set.
stability	number	No	0.5	0	1	-	Higher values make the voice steadier and more consistent; lower values make it more varied and expressive.
similarityBoost	number	No	0.75	0	1	-	How closely the output matches the original voice; higher values track it more tightly but can amplify artifacts.
styleExaggeration	number	No	0	0	1	-	Amplifies the speaker’s style and emotion; higher values are more expressive but can reduce stability.
speed	number	No	1	0.7	1.2	-	How fast the speech is delivered; below 1.0 slows it down, above 1.0 speeds it up. Extreme values may affect quality.
outputFormat	string	No	mp3_44100_128	-	-	mp3_22050_32, mp3_24000_48, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, wav_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192	File type, sample rate, and bitrate of the generated audio.
seed	number	No	-	-	-	-	Fixes randomness so identical inputs produce the same audio every time.