Lyria 3 Pro

Google Lyria 3 Pro — generate a full, structured song (up to ~3 min) from a single style/mood prompt. Writes its own lyrics from the prompt (no separate lyrics input); include genre, mood, instrumentation, tempo and vocal style in the prompt for best results. Takes ~3 min to render and is SynthID-watermarked. Optional `image_url` steers mood/theme from a reference image. The `lyrics` output is a TEXT description of the track (style/production notes, sometimes the sung lines) — NOT timed/timestamped lyrics — available to wire into a downstream node but not shown on the node's own card.

Try Lyria 3 Pro in the playground

Last updated View as MarkdownAgent setup

Lyria 3 Pro

Badge: music
Node type: audio:lyria3_pro
Category: audio

Description

Lyria 3 Pro is Google's model for turning a style and mood prompt into a full, structured song of up to about three minutes: describe the genre, mood, instrumentation, tempo and vocal style in Prompt, optionally wire an image into Mood Reference (optional) to steer the mood or theme, and run the node. It returns the song as Generated Audio, plus Lyrics / Song Notes, a text description of the track with style and production notes and sometimes the sung lines. Those notes are not timed lyrics and do not show on the node's card, so wire them into a downstream node to use them. There is no separate lyrics input, because Lyria writes its own lyrics from your prompt. A song takes about three minutes to render, is SynthID-watermarked, and costs about 20 credits per song.

Pricing

  • Cost: ~20 credits per song

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
prompt Prompt TEXT (required) · multiline — Genre, mood, instrumentation, tempo and vocal style — e.g. "An energetic electronic dance track with soaring synth leads, punchy four-on-the-floor kick drums... 128 BPM." Lyria writes its own lyrics from this.
image_url Mood Reference (optional) IMAGE — Optional image whose mood/theme steers the generated music.

These render as form fields in the right-side config panel when the node is selected.

No sidebar config fields.

Outputs

ID Label Type
audio Generated Audio AUDIO
lyrics Lyrics / Song Notes TEXT

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.