The model makes the clip. Video API makes it ready to ship.

Lyria 3 Pro Preview

Audio·gemini·by Google

Lyria 3 Pro generates full-length songs from text or image prompts, returning high-fidelity MP3 audio with vocals, lyrics, and song structure.

Try it now →
API reference
Runtime (p50)
1m
Estimated price
$0.08
Call the API
prediction.sh
sh
curl -X POST \
  -H "Authorization: Bearer $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "lyria-3-pro-preview",
    "version": "0.0.1",
    "input": {
        "prompt": "A cinematic indie-pop song with warm analog synths, atmospheric electric guitar, soft piano, deep rounded bass, and expressive live drums. Dreamy female vocals with an intimate, emotional delivery gradually build into a powerful uplifting chorus. Nostalgic yet modern production, spacious reverb, subtle vocal harmonies, rich stereo atmosphere, emotional nighttime-drive feeling. Start minimal and intimate, then slowly expand into a wide cinematic climax. 105 BPM.",
        "image_urls": [
            "https://cdn-us.eachlabs.ai/defaults/c40d3fd449db4dc592f5f58b47236b52.webp"
        ]
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models
MiniMax Music 3.0 AI model preview
MiniMax Music 3.0Minimax
ACE-Step 1.5 | Text to Music AI model preview
ACE-Step 1.5 | Text to Musiceachlabs
Mureka | Generate Instrumental AI model preview
Mureka | Generate InstrumentalMureka
Mureka | Create Speech AI model preview
Mureka | Create SpeechMureka
* FAQ

About Lyria 3 Pro Preview

01 / 03

What is Lyria 3 Pro Preview?

Lyria 3 Pro Preview is a Google music generation model for creating full-length songs from text or image prompts. It can return high-fidelity audio with vocals, lyrics, and song structure, making it useful for complete musical drafts rather than short clips.