Compare · Audio
Eleven Music vs Lyria 3
Specs, pricing, and capabilities side by side — plus outputs generated from identical prompts, so the only variable between the columns is the model.
Cloud
Remove from comparison
ElevenLabs music generation model for creating original AI-composed tracks.
Learn more about Eleven Music →Cloud
Remove from comparison
Enhanced Lyria model with improved musical coherence and audio quality.
Learn more about Lyria 3 →Overview
Creator
ElevenLabs
Google
Available on
Replicate
Replicate
Model ID
elevenlabs/music
google/lyria-3
Specs
Pricing
$0.0083 per second
$0.04 per generation
Type
Music generation
Music generation
Max length
Up to 5 min
—
Output formats
MP3, WAV_16KHZ, WAV_22KHZ, WAV_24KHZ, WAV_CD_QUALITY
—
Negative prompt
—
Supported
Seed control
—
Supported
Samples
AmbientTexture and restraint
PromptSlow ambient piece for a rainy morning: warm analog pads, soft tape hiss, and a simple four-note piano motif repeating. No drums.
0:00 / 0:10
0:00 / 0:30
CinematicArrangement and dynamic build
PromptCinematic orchestral build: low strings and a distant horn, tension rising over eight bars into a full brass swell with timpani.
0:00 / 0:10
0:00 / 0:30
ElectronicRhythm, groove, and low end
PromptDowntempo electronic groove at 96 BPM: dusty breakbeat, deep sub bass, a filtered Rhodes chord stab, and light vinyl crackle.
0:00 / 0:10
0:00 / 0:30
Every sample is the model’s first result for the shared scene prompt — no cherry-picking — generated via Replicate or Runware. Hover a copy icon to read the full prompt.
Popular comparisons
Claude Fable 5 vs GPT 5.6 SolGemini 3.1 Pro vs GPT 5.6 SolClaude Fable 5 vs Gemini 3.1 ProGPT 5.6 Sol vs Grok 4.3Claude Sonnet 4.6 vs Gemini 3.5 FlashNano Banana 2 vs GPT Image 2Flux 2 Pro vs Seedream 5 ProSeedream 5 Pro vs Nano Banana 2Eleven v3 vs Gemini 3.1 Flash TTSLyria 3 vs Music 2.6Seedance 2.0 vs Veo 3.1Veo 3.1 vs Kling 3.0Kling 3.0 vs Gen-4.5