Lyria 3 Pro and Lyria 3 Clip are now in Gemini API and AI Studio, with Lyria 3 Pro priced at $0.08 per song and able to structure tracks into verses and choruses. That gives developers a clearer path to longer-form music features, with watermarking and prompt design built in.
The launch is two separate music endpoints, not one tiered mode. Google's product intro calls them "our full song and 30 second music models," and the more detailed launch thread says Lyria 3 Pro is for multi-minute songs while Lyria 3 Clip is for short-form generation. Google also published music docs alongside the rollout and linked a broader launch blog for implementation details.
The API surface already looks like standard Gemini model invocation. In the
, the Python example calls client.models.generate_content with model="lyria-3-clip-preview", asks for response_modalities=["AUDIO", "TEXT"], and writes the returned inline audio bytes to an MP3. That matters for teams already using Gemini SDK patterns: music generation lands as another model call rather than a separate stack.
Google's pricing and controls are unusually concrete for a first-day media API: Pro costs $0.08 per generated song, Clip costs $0.04, and prompts can control tempo, request time-aligned lyrics, and use image-to-music inputs. The same post says Pro generates "full songs" while Clip is tuned for 30-second outputs.
The differentiator for Pro is track structure. DeepMind's longer tracks post says developers can "map out intros, verses, choruses, and bridges" and extend compositions to 3 minutes, which moves the model beyond loop-like background snippets. Gemini's reference image tip adds a practical prompt trick: when you upload a reference image with a Pro prompt, the image becomes context for both lyrics and cover art.
Google is shipping provenance with the model. The SynthID details say all outputs are embedded with SynthID, described as an "imperceptible watermark," and that users can upload a file to Gemini and ask whether it was generated with Google AI. That gives product teams a built-in detection path if they need origin checks in moderation or publishing flows.
Rollout is split between developer and consumer surfaces. DeepMind's rollout note says developers can build with the API in Google AI Studio, while paid Gemini subscribers get access in the app; Gemini's app demo shows the mobile flow under "Create Music" with "Thinking" and "Pro" model options. The result is a new API for music features, plus an end-user interface that can double as a fast prompt-testing environment.
Data Agent Benchmark launches with 54 enterprise-style queries across 12 datasets, nine domains, and four database systems, while the best frontier model reaches only 38% pass@1. It gives teams a stronger eval for cross-database agents than text-to-SQL-only benchmarks.
breakingMalicious LiteLLM 1.82.7 and 1.82.8 releases executed .pth startup code to steal credentials and were quarantined after disclosure. Rotate secrets, audit transitive AI-tooling dependencies, and add package-age controls before letting agents install packages autonomously.
breakingTurboQuant claims 6x KV-cache memory reduction and up to 8x faster attention on H100s without retraining or quality loss on long-context tasks. If those results hold in serving stacks, teams should revisit long-context cost, capacity, and vector-search design.
releaseOpenCode is adding remote sandboxes, synced state across laptop, server, and cloud, and more product surface inside its plugin system. That makes long-running off-laptop workflows more practical, but operators should still review telemetry, sandbox, and exposure defaults.
releaseClaude Code 2.1.84 adds an opt-in PowerShell tool, new task and worktree hooks, safer MCP limits, and better startup and prompt-cache behavior. Anthropic also documented auto mode’s action classifier and added iMessage as a channel, so teams should review permissions and remote-control workflows.
Introducing Lyria 3 Pro and Lyria 3 Clip, our full song and 30 second music models, available starting today in the Gemini API and our all new music experience in @GoogleAIStudio!!
All Lyria 3 and Lyria 3 Pro outputs are embedded with SynthID, our imperceptible watermark for identifying Google AI-generated content. Simply upload a file and ask Gemini if it was generated using Google AI, and Gemini will check for SynthID. Show more
Today, we’re releasing Lyria 3 music generation models (Pro/Clip) in @GoogleAIStudio and Gemini API! 🎵 - Lyria 3 Pro generates full songs (minutes, controllable via prompt), $0.08/song. - Lyria 3 Clip creates 30-second audio clips, $0.04/song. - Control tempo, time-aligned Show more
