Lyria 3.5 doubles as a TTS model: one prompt yields eerily natural 60-second speech

fofrAI · x · 2026-09-06

fofrAI found that Google's music-generation model Lyria 3.5 can be prompted as a text-to-speech model, producing raw sound bites that "seam real."
Example prompt: "just a british millennial woman talking with a feeling of being jaded, candid and natural, no lyrics, no music, no beats, no percussion, just 60 seconds long."
The output is conversational speech rather than singing, suggesting the model's underlying capability extends well beyond its official music focus — a non-obvious trick worth testing for voice and audio content workflows.

More from Multimodal