Lyria 3.5 Can Work as TTS, Generating Realistic Speech from One Prompt

fofrAI discovered that Google's music model Lyria 3.5 can be prompted like a text-to-speech model, producing highly realistic raw speech clips up to 60 seconds from a single prompt.

2026-09-06 ~ 2026-09-07 · 2 related posts

• Lyria 3.5 doubles as a TTS model: one prompt yields eerily natural 60-second speech — fofrAI · 2026-09-06

1 near-duplicate retellings: arnicas