ElevenLabs Models: The Essentials

ElevenLabs builds most of Scenario's audio models: full songs, expressive speech, voice transformation, dubbing, and sound effects. This article covers all thirteen ElevenLabs models on the platform, with one example each: Music v2.5, Music Advanced v2.5, Music Extend v2.5, Music v2, Music Advanced v2, 3 (Alpha), Multilingual v2, Turbo 2.5, Voice Changer, Voice Isolator, Speech to Speech, Dubbing v2, Dubbing, and Sound Effects 2.

Music

Full tracks generated from text. Music v2.5 takes one prompt and writes a whole song. Music Advanced v2.5 builds a song section by section, with its own styles, lyrics, and duration per part. Both are the current recommended versions; Music v2 and Music Advanced v2 remain available but are superseded. For a full walkthrough of prompting either v2.5 model, see the dedicated "ElevenLabs Music v2.5: The Essentials" article.

ElevenLabs Music v2.5

One text prompt in, one complete track out: any genre, vocal or instrumental, 3 to 600 seconds.

Uplifting pop anthem, vocal chorus · Open on Scenario

Warm neo-soul groove with vocal ad-libs · Open on Scenario

Synthwave chase, instrumental · Open on Scenario

5-second brand sting, the shortest supported length · Open on Scenario

5-minute long-form cinematic score, near the 600s maximum · Open on Scenario

ElevenLabs Music Advanced v2.5

Compose a song as an ordered list of sections, each with its own styles, lyrics, duration, and a context-adherence dial.

Pop anthem, verse and chorus · Open on Scenario

ElevenLabs Music Extend v2.5

Reworks an existing track instead of starting from a blank prompt: keep the sections you want unchanged and generate new intros, verses, bridges, or outros around them. For the full parameter reference and more examples, see the dedicated "ElevenLabs Music v2.5: The Essentials" article.

Kept the original 24s verse and chorus, generated a new bridge · Open on Scenario

ElevenLabs Music v2 (legacy)

The previous generation of the single-prompt model. Superseded by Music v2.5.

Morning sun rising over the beach (legacy Music v2) · Open on Scenario

ElevenLabs Music Advanced v2 (legacy)

The previous generation of the composition-plan model. Superseded by Music Advanced v2.5.

Epic orchestral cinematic score (legacy Advanced v2) · Open on Scenario

Text to Speech

Convert written text into spoken audio, choosing a built-in voice or a cloned one.

ElevenLabs 3 (Alpha)

The most expressive ElevenLabs voice model: 70+ languages, steered with inline tags like [whispers] or [excited] for emotion, pacing, and emphasis.

"[low][dark] Welcome... to my domain." Inline emotion tags steering delivery · Open on Scenario

ElevenLabs Multilingual v2

Natural, emotionally rich speech in 29 languages, with 21 built-in voices or a cloned one.

Greek: "Είμαι καλά! Θέλεις να πάμε μια βόλτα το απόγευμα;" · Open on Scenario

ElevenLabs Turbo 2.5

Low-latency text to speech in 32 languages, tuned for near real-time use.

“Don't make a sound... please.” Whispered delivery at low latency · Open on Scenario

Voice Transformation

Re-voice an existing recording rather than generating speech from scratch, preserving the original words, timing, and emotion.

ElevenLabs Voice Changer

Transform any voice recording into one of 21 preset voices or a cloned voice.

Narration re-voiced with a preset voice · Open on Scenario

ElevenLabs Voice Isolator

Strips background noise, music, and ambient sound from audio or video, returning a clean isolated vocal track.

Isolated vocal from a noisy concert-floor recording · Open on Scenario

ElevenLabs Speech to Speech

Re-voices any recording into 21 preset voices or a custom cloned voice, preserving words, timing, and delivery.

Guided underwater adventure, re-voiced · Open on Scenario

Dubbing

Translate the speech in a video or audio file into another language while preserving each speaker's voice, tone, and timing.

ElevenLabs Dubbing v2

Automatic dubbing into 31 languages with source auto-detection and keyterms to keep names and brand terms intact.

City-street b-roll, dubbed to Mandarin with voice preserved · Open on Scenario

ElevenLabs Dubbing

Dubs video or audio into 30 languages via voice cloning, auto-detecting up to 10 speakers, with optional background-audio removal.

Dialogue scene, dubbed to Portuguese · Open on Scenario

Sound Effects

ElevenLabs Sound Effects 2

Generates custom SFX from a text description: clips up to 30 seconds, seamless looping, and adjustable prompt influence.

"Blacksmith forge: rhythmic hammering on anvil, crackling fire, bellows pumping" · Open on Scenario

Open the models: Music v2.5 · Music Advanced v2.5 · Music v2 · Music Advanced v2 · ElevenLabs 3 · Multilingual v2 · Turbo 2.5 · Voice Changer · Voice Isolator · Speech to Speech · Dubbing v2 · Dubbing · Sound Effects 2