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.
Related event: Lyria 3.5 Can Work as TTS, Generating Realistic Speech from One Prompt(2 posts)→
More from Multimodal
- Two Midjourney sref codes for grainy pastel fashion illustration style — sergeantsref · 2026-10-23
- Three free ways to try MOSS-Image: API playground, HF Space, ComfyUI — songguoxiansen · 2026-10-23
- Open-source MOSS-Image tops 1M ComfyUI downloads, 5B model rivals closed rivals — songguoxiansen · 2026-10-23
- GAFU Uses Generation-Side Representations to Boost Fine-Grained Visual Understanding in Unified Multimodal Models — Tengju Ru · 2026-10-23
- MiniMax Design MCP goes live: create with Design inside Codex and other agents — Hailuo_AI · 2026-10-23
- Quiver's detailed SVG generation sparks debate: code-drawn images could replace pixel-based image models — stuffyokodraws · 2026-10-23