Voice Design Launches: Prompt-to-Voice Generation With Best-in-Class Accent Fidelity
udmrzn · x · 2026-09-09
Gradium (neilzegh) announced Voice Design: describe accent, age, gender, and pace in a prompt, and get new usable voices in seconds — live and free in the Gradium API and Studio. The team says the underlying model was first built for internal voice curation, now claims best-in-world accent fidelity, with unexposed zero-shot abilities and big updates coming soon.
Related event: Gradium Launches Voice Design: Custom Voices from a Single Prompt(5 posts)→
More from Multimodal
- Kling 3.0 cuts credits 20%, adds native 4K audio and Motion Control — aziz4ai · 2026-09-09
- Codex + Magnific MCP + PixVerse skill turns one idea into a finished 4K video — aziz4ai · 2026-09-09
- MiniMax H3 lands on Runware: Turbo at half price, 75% off from $0.01/second — aziz4ai · 2026-09-09
- Game dev generates all character animations with GPT-6 Astra via Blender MCP — _amirabs · 2026-09-09
- Suno rolls out music models built with industry partners, introducing royalty payments to labels — Polymarket · 2026-09-09
- GPT-6 Astra builds 3D games, Blender scenes and anatomy models from almost nothing — minchoi · 2026-09-09