Paris-based voice AI company Gradium has rolled out a new feature called Voice Design, allowing users to generate entirely new synthetic voices from a text description in a matter of seconds. The company said the tool does not require reference audio, which also removes the need to handle related copyright issues tied to source clips. Voice Design is now available through Gradium’s API and Studio platform, and the feature is included across all plans, including the free tier.
Users can define attributes such as gender, age, accent, pitch, and speaking speed when generating a voice. The system supports English, French, Spanish, Portuguese, and German. For each request, it can return between one and five candidate voices, typically within three to five seconds. Gradium said the generated voices can also be used directly for streaming through its text-to-speech endpoint.
According to blind test results released by the company, Voice Design achieved a 72.6% win rate in accent-prompt comparison tests, ahead of competitors including ElevenLabs and Inworld. Gradium added that the product shows a clear edge in generating regional accents such as Quebec French and Bavarian German.
Gradium, a voice AI company based in Paris, has introduced Voice Design, a feature that lets users create entirely new synthetic voices from a text description in seconds, according to Techub News. The company said no reference audio is required, removing the need to deal with copyright issues tied to source recordings.
Voice Design is now live on Gradium’s API and Studio platforms, and it is available across all pricing tiers, including the free plan. Users can specify traits such as gender, age, accent, pitch, and speaking speed to shape the generated voice. The feature supports English, French, Spanish, Portuguese, and German. Each request can produce between one and five candidate voices, usually within three to five seconds. The generated voices can then be used directly for streaming through Gradium’s text-to-speech endpoint.
Gradium also released blind test results showing that Voice Design posted a 72.6% win rate in accent-prompt comparison tests, outperforming rivals including ElevenLabs and Inworld. The company said the system is particularly strong at generating regional accents, citing Quebec French and Bavarian German as examples.
The report cited MarkTechPost.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
