Lyria

At a glance

Audio

Content CredentialsA signed record (C2PA) of how the file was made, sealed so any change shows.

Not stated. None of Google's pages listed under Sources read says so.

Google Cloud documentation lists two Lyria 3 preview models among models whose "images or videos" Google LLC signs with Content Credentials, but does not say that audio output is signed.

Invisible watermarkA signal woven into the pixels, frames, audio or wording, meant to survive copying.

Gemini API documentation says all audio from its Lyria music generation includes an imperceptible SynthID audio watermark, and Google DeepMind's Lyria page says all its tracks are watermarked with SynthID.

Google's pages differ on robustness. Its SynthID page says the audio watermark can't be altered by common modifications such as added noise, MP3 compression or speed changes; Gemini Apps Help says a watermark may not be detected after many alterations.

Music generation (Lyria), Gemini APIGoogle AI for Developers

Quoted passage Limitations: Watermarking

Watermarking : All generated audio includes a SynthID audio watermark for identification. This watermark is imperceptible to the human ear and does not affect the listening experience.

Lyria 3.5 — Google DeepMindGoogle DeepMind

Quoted passage responsibility section

All of our tracks are imperceptibly watermarked with SynthID technology, allowing you to detect whether music has been created or edited using AI.

Google SynthIDGoogle DeepMind

Quoted passage AI-generated audio

SynthID embeds a watermark into any audio generated or published through our AI music generation model Lyria or the podcast generation feature of Notebook LM. It’s inaudible to the human ear, and can’t be altered by common modifications like adding noise, MP3 compression, or changing the speed of the track

Verify AI-generated images, videos, and audioGoogle (Gemini Apps Help)

Quoted passage For SynthID; Common questions about SynthID

In some cases it isn’t clear if the image or video was created or edited by Google AI or not. Some common reasons for this are: "Not enough details to watermark" (e.g., very simple or abstract content). "Likely too small an edit" (minor alterations might not carry a detectable watermark)." "Yes. The digital watermark will usually still exist even if the image, video, or audio is re-scaled, re-colored, compressed or altered in other ways. However, there's still a chance that after many alterations the watermark won’t be detected.

AI label in metadataA plain metadata field (IPTC Digital Source Type) saying AI made the content. Anyone can add or remove it.

Not stated. None of Google's pages listed under Sources read says so.

Visible markA mark you can see, such as a logo or a sparkle in a corner.

Not stated. None of Google's pages listed under Sources read says so.

Tool named in metadataThe tool or model written into ordinary file fields, such as Software or Creator.

Not stated. None of Google's pages listed under Sources read says so.

Limits and detection

Checking tool from the makerA way the maker offers to check a file for its traces.

Google said on October 7, 2026 that its SynthID Detector is available to everyone, globally in English.

We're making it easier to identify AI-generated content globally.Google (The Keyword blog, Africa edition)

Quoted passage body

Since launching Google SynthID in 2023, we've helped people identify AI-generated media using imperceptible watermarks across images, video, and audio. To date, we've watermarked over 180 billion images and videos, along with 240,000 years of audio content." "Last year, we introduced an early version of the SynthID Detector to help media professionals verify AI-generated content. Now, we’re expanding access to everyone – with the tool available globally in English starting today.