Google releases Lyria 3 Clip Preview for music generation via API
Google has released Lyria 3 Clip Preview, a music generation model available through the Gemini API as of March 30, 2026. The model generates 30-second audio clips from text prompts or images at $0.04 per clip, with a 1,048,576 token context window.
Google Lyria 3 Clip Preview — Quick Specs
Google Releases Lyria 3 Clip Preview Music Generation Model
Google has launched Lyria 3 Clip Preview, a music generation model available through the Gemini API starting March 30, 2026. The model generates short audio clips, loops, and previews from text prompts or images.
Key Specifications
Context Window: 1,048,576 tokens
Pricing: $0.04 per 30-second audio clip. Input and output token pricing is listed as $0/M, suggesting the per-clip pricing model supersedes traditional token-based billing.
Audio Quality: The model generates high-quality, 48kHz stereo audio with structural coherence, including vocals, timed lyrics, and full instrumental arrangements.
Capabilities
Lyria 3 Clip is part of Google's broader Lyria 3 family of music generation models. It can:
- Generate audio from text prompts
- Generate audio from images
- Produce clips up to 30 seconds in duration
- Create loops and preview content
- Generate vocals with synchronized lyrics
- Arrange full instrumental compositions
Availability
The model is accessible through the Gemini API and is routed through OpenRouter, which handles provider selection and fallback management for uptime optimization. Developers can access the model using OpenAI-compatible APIs or through the OpenRouter SDK.
Usage data shows current demand, with prompt activity at 410K and completion activity at 280K tokens tracked across the platform in recent monitoring periods.
What This Means
Google enters the consumer music generation market with a pricing model that simplifies billing compared to token-based systems—developers pay per 30-second clip rather than tracking input/output token consumption. The 1M+ token context window is a technical feature that likely supports longer creative instructions or batch processing capabilities, though typical use cases focus on discrete clip generation. This positions Lyria 3 Clip as a tool for music preview generation, loop creation, and short-form content production, competing with existing music AI tools at a transparent, clip-based price point.
Related Articles
Google DeepMind's New Chief Prioritizes Fast Gemini 4 Release Over AGI Debate
Google DeepMind's new head Koray Kavukcuoglu says Gemini 4 is in early post-training and could ship well before year-end, following the quiet cancellation of Gemini 3.5 Pro. He downplayed the AGI question that defined predecessor Demis Hassabis's tenure, calling it 'not the right conversation.'
Google Launches Gemini 3.8 Flash TTS: Voice Cloning and Text-Described Voices for $9-18 per Million Audio Tokens
Google has released Gemini 3.8 Flash TTS and Flash-Lite TTS, two speech generation models that let users design voices from text descriptions or clone a voice from a 30-second sample. Both support over 100 languages and roll out now through the Gemini API and Google AI Studio.
Nvidia Releases Nemotron 3 Diarization, a Free 100M-Parameter Model That Tracks 8 Speakers in Real Time
Nvidia released Nemotron 3 Diarization, a free 100-million-parameter model that identifies who is speaking in real time across up to eight participants. It leads the VoiceArena Diarization Benchmark v1 with a 14.7% error rate, cutting errors by 41% versus its predecessor.
Apple Releases LensVLM-9B, a 9B Vision-Language Model That Selectively Decompresses Text Images
Apple has released LensVLM-9B, a 9-billion-parameter vision-language model fine-tuned from Qwen3.5-9B-Base that processes documents as compressed images, selectively expanding only relevant pages to full resolution. The model supports 5x, 10x, and 15x compression ratios and is available under Apple's Machine Learning Research Model License.
Comments
Loading...