Freedom251 › AI Podcast Music Generators
Google Lyria

What Google Lyria is
Google Lyria is a paid music-generation service available through the web and an API, with no free plan. It creates music from prompts, including instrumental arrangements, lyrics and sung vocals across many genres and styles. Lyria 3.5 accepts text or images, writes lyrics in the prompt’s language, and adapts vocal style and pronunciation to that language. Lyria 3 Clip produces 30-second MP3 clips for loops, previews and other short uses. Lyria 3.5 creates MP3 songs lasting a couple of minutes, with duration influenced by the prompt. The API outputs high-fidelity 44.1 kHz stereo audio. Google distributes Lyria 3.5 through Google Flow Music and says downstream providers may access the models through an API under applicable terms. Generated audio carries an imperceptible SynthID watermark. Safety filters block requests such as specific artist voices or copyrighted lyrics. Generation is single-turn, so clips cannot be refined through follow-up prompts, and repeated calls may differ.
Who it suits
Lyria suits people creating prompted music with vocals, lyrics or instrumental arrangements. It is available to web users and API developers who accept paid access and the stated content restrictions.
What it does well
- Generates vocals, lyrics and instrumental arrangements
- Lyria 3.5 accepts text or image prompts
- Creates 30-second clips for loops and previews
- API outputs 44.1 kHz stereo audio
- Supports lyrics in the prompt’s language
What to know first
- No free plan is available
- Generation does not support iterative prompt refinement
- Results can vary between identical calls
- Safety filters block artist voice requests and copyrighted lyrics
Plans
| Plan | Billed and limits | Price |
|---|---|---|
| Lyria 3 Clip Preview | 30 seconds | On request |
| Lyria 3 Pro Preview | Full-song music generation | On request |
| Lyria 3.5 Full Song | Full-song music generation | On request |
| Lyria 3.5 (Full Song) — Gemini API | per song · Free tier not available | $0.08, paid once |
As deepmind.google lists them, read 21 Sept 2026. The maker's own page has the final word.
Verdict
Google Lyria covers short clips and couple-of-minute songs, with vocal generation and multilingual lyrics. Its paid access, single-turn workflow and prompt restrictions are important considerations.
Facts from Google Lyria's own pages
- Access channels
- Lyria 3.5 is distributed through Google Flow Music, and Google says downstream providers can access its models through an API subject to applicable terms. · deepmind.google, 12 Oct 2026
- Audio quality
- The API produces high-fidelity 44.1 kHz stereo audio. · ai.google.dev, 12 Oct 2026
- Editing limit
- Lyria 3.5 generation is single-turn and does not support refining a generated clip through multiple prompts. · ai.google.dev, 12 Oct 2026
- Free plan
- No · deepmind.google, 21 Sept 2026
- Full songs
- Lyria 3.5 generates MP3 full-length songs lasting a couple of minutes, with duration influenced by the prompt. · ai.google.dev, 12 Oct 2026
- Image input
- Lyria 3.5 can generate music from text prompts or images. · ai.google.dev, 12 Oct 2026
- Intended users
- Google describes Lyria as a model for creating high-quality music across a wide range of genres and styles. · deepmind.google, 12 Oct 2026
- Languages
- Lyria 3.5 generates lyrics in the language of the prompt and adapts vocal style and pronunciation to match. · ai.google.dev, 12 Oct 2026
- Maximum track length
- 0.5 · deepmind.google, 21 Sept 2026
- Output variability
- Results may vary between calls, even when the same prompt is used. · ai.google.dev, 12 Oct 2026
- Supported platforms
- web · deepmind.google, 21 Sept 2026
- Purpose
- Lyria generates high-quality music from prompts, including full songs with vocals, lyrics, and instrumental arrangements. · ai.google.dev, 12 Oct 2026
- Responsible development
- Google says Lyria 3.5 underwent human and automated evaluations, specialist red teaming, and ethics and safety reviews before release. · deepmind.google, 12 Oct 2026
- Safety and watermarking
- Generated audio includes an imperceptible SynthID watermark, and prompts are checked by safety filters that block requests such as specific artist voices or copyrighted lyrics. · ai.google.dev, 12 Oct 2026
- Short clips
- Lyria 3 Clip generates 30-second MP3 clips intended for short clips, loops, and previews. · ai.google.dev, 12 Oct 2026
- Use restrictions
- Google's prohibited-use policy rules out uses involving dangerous or illicit activity, rights violations, service security compromises, harmful content, or misinformation. · deepmind.google, 12 Oct 2026
- Vocal generation
- Yes · deepmind.google, 21 Sept 2026
Where Google Lyria stands on Freedom251
- AI Podcast Music Generators#31 of 36
- AI Music Generators#112 of 123