Gradium Launches Voice Design: Custom Voices from a Single Prompt

Gradium, a voice AI company incubated by Kyutai, has launched Voice Design: users write a single prompt describing accent, age, gender, and speaking pace, and a ready-to-use custom voice is generated within seconds. The feature is live in both the Gradium API and Studio, free of charge.

Confirmed

• Voice Design generates custom voices from natural-language prompts covering accent, age, gender, and pace, returning results in seconds.
• The feature is available now in the Gradium API and Studio, free to use.
• The company says the underlying model was originally built for internal screening of client voices and is now opened to the public.
• Users have tested it: amritwt generated a custom voice, another user requested a "male in his 20s with a crisp, practical contemporary Singaporean English accent," and ThePeterMick generated a voiceover voice, showing it works out of the box for ordinary users.

Why it matters

• Voice customization previously required voice cloning recordings or professional tuning; Voice Design lowers the barrier to a single sentence of description, sharply cutting personalization costs for voiceover, audio content, and in-app speech.
• Free API access enables low-cost integration for developers and may intensify competition in the speech synthesis market.

2026-09-09 ~ 2026-09-10 · 6 related posts

• [source] Gradium launches Voice Design: prompt-to-voice generation, free in API and Studio — ThePeterMick · 2026-09-09
• Gradium launches Voice Design: prompt-to-voice generation, free in API and Studio — bigaiguy · 2026-09-09
• Voice Design Launches: Prompt-to-Voice Generation With Best-in-Class Accent Fidelity — udmrzn · 2026-09-09
• Gradium, from Kyutai's lab, launches Voice Design: prompt-to-voice in seconds, free in API — RemiCadene · 2026-09-10

2 near-duplicate retellings: Scobleizer · thisdudelikesAI