Shotcraft
Music and sound

Google Lyria 3 Pro

Generates full songs with vocals and timed lyrics from a text prompt, optional user-supplied lyrics and up to ten reference images, at up to about three minutes with structural sections (intro, verse, chorus, bridge).

An audio model by Google · read 2026-08-14 · sourcing high

Up to
180 seconds
Resolution
44.1 kHz stereo; MP3 by default, WAV optional
Weights
Not released
API
Yes
Commercial use
Permitted subject to conditions

Available via the Gemini API and Vertex AI (public preview) and in Google AI Studio, Google Vids, the Gemini app and ProducerAI. Single-turn only: there is no iterative editing of a generated track.

Commercial use — Permitted subject to conditions

Google does not publish an output-ownership clause on the Lyria model pages; commercial use is governed by the applicable Google Cloud / Gemini API terms plus the Generative AI Prohibited Use Policy (https://policies.google.com/terms/generative-ai/use-policy).

Who owns the output: depends on your plan tier

  • Depends on your plan tier. The specific per-tier commercial rights and any indemnification were NOT verified from a terms page in this pass
  • The terms restrict what you may generate. Google does not publish an output-ownership clause on the Lyria model pages; commercial use is governed by the applicable Google Cloud / Gemini API terms plus the Generative AI Prohibited Use Policy (https://policies.google.com/terms/generative-ai/use-policy)
  • Output is watermarked. Every output carries an imperceptible SynthID watermark at bitstream level and supports C2PA content credentials - relevant if you need to disclose AI content or if a platform detects it

The conditions above were extracted from the licence notes recorded during research, and each one shows the sentence it came from so you can check the reading. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Google's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is strong: the figures came from pages we retrieved and read. Check the vendor's current documentation

What it takes in
text, lyrics, image
What it makes
audio
Maximum duration
180 seconds
Maximum resolution
44.1 kHz stereo; MP3 by default, WAV optional
Controls
lyrics-input, style-prompting, instrumental-only
Weights
Not released
API
Yes
Pricing
Per-song API pricing. Gemini API pricing lists 'Lyria 3 Pro Preview (Full Song)' at $0.08 per song, with no free tier. Also billed through Vertex AI; the Vertex generative AI pricing page could not be parsed to confirm the Vertex rate.
Released or updated
2026-04-08

Strengths

  • Enterprise-grade API access with per-song pricing
  • Automatic lyric generation plus custom lyric input
  • Image conditioning (up to 10 images) for mood/style
  • 44.1 kHz stereo with WAV output option
  • SynthID watermarking and C2PA for provenance

Weaknesses

  • Public preview; rate limits are more restrictive and behaviour may change
  • Single-turn only - no iterative editing, no stems, no extend
  • Non-deterministic across identical prompts
  • Output ownership and indemnity terms are not stated on the model documentation
  • All output is watermarked

Best for

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

MCP servers that front Google

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Google Lyria 3 Clip

The short-form Lyria 3 variant, model ID lyria-3-clip-preview, which produces a fixed 30-second clip from a text prompt with optional lyrics and image

Music and sound

Google Lyria RealTime

An experimental streaming music model (models/lyria-realtime-exp) that generates continuous instrumental music over a bidirectional WebSocket while yo

Music and sound

ACE-Step

An open-source music generation foundation model combining diffusion with a lightweight linear transformer, released May 2025 by ACE Studio and StepFu

Music and sound

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.