Gemini TTS tip: specifying accents in the prompt unlocks far better non-English performance
juberti · x · 2026-09-19
In a thread about Gemini TTS voice quality, juberti and others clarify that the "accented English" voices actually work reasonably well for many other languages — and the best results come from explicitly naming the accent (or target language) in your instruction prompt. Screenshots circulating online don't tell the whole story: testers are advised to declare the accent/language in the prompt before judging multilingual performance, and juberti invites feedback on how Spanish specifically holds up.
More from Multimodal
- Experimental video mixes visual styles, generated with Seedance 2.5 on Adobe Firefly — umesh_ai · 2026-11-04
- Hailuo AI claims H3 scored perfect on language tests; Japanese creator praises its Japanese signage fidelity — Hailuo_AI · 2026-11-04
- YANAMI: 400K-dialog multimodal dataset shows models still fail at stateful multiturn interaction — Shengyu Wang · 2026-11-04
- Open-source Idol model turns a single image into 3D in 45s on 8GB VRAM — Promptmethus · 2026-11-04
- ComfyUI v0.44.0 released with new Patina texture nodes — Fcking_Chuck · 2026-11-04
- Krea 3 technical report released: a deep dive into data, architecture and training — bdsqlsz · 2026-11-04