Following your feedback, we’ve broadened the range of voices available in Speech Synthesis and in Projects Alpha. We’re excited to say these voices are the product of Professional Voice Cloning capabilities and were created in partnership with industry professionals, bringing new quality and versatility to our platform.
Our expanded range now offers:
- A wider range of delivery styles - from serene and gentle to profound and intense, catering to a multitude of creative needs: be it for cartoons, video games, audiobooks, or podcasts.
- A broader selection of accents, including more British and American dialects, alongside newly introduced Irish, Swedish, and Italian accents.
- Overall audio quality improvements, promising rich and crisp voice output.
All the voices are now also easier to explore and select thanks to better dropdown and filtering mechanisms.
The new voices were created in partnership with voice actors to enhance the quality of our tools by leveraging their unique expertise. They also serve as a showcase for our soon-to-be-released Professional Voice Cloning model which we trained the new voices on, based on 30-minute recordings of specific delivery styles.
We don’t hold the copyrights to these voices; we simply license them. This provides the voice actors with the freedom and flexibility to end the partnership as they see fit after a predetermined period, currently set to 1 year.
We will also provide voice actors with other partnership models as we expand our platform’s voice sharing mechanisms. We see a future where Voice AI companies and voice actors collaborate to build new ways of working together. Soon, we hope to launch a set of new compensation initiatives to improve this potential for cooperation, while prioritizing fair practices.
For the current release, we worked closely with voice actors to create AI voices that are within the actors’ range and comfort level. We also enabled them to explore vocal styles which aren't their primary focus, if they wished to, offering them an avenue for additional experimentation and compensation.
We are actively exploring other partnership models, including remunerating voice actors per-voice-generation, with trials beginning over the next few months. Over time, we hope to introduce more custom pricing mechanisms. Our current release is the first step towards establishing an ever more sustainable collaboration model while we refine our practices. We are deeply mindful of the crucial role that voice actors play in shaping our platform and Voice AI in general.
If you are a Voice Actor interested in sharing your thoughts or working with us, please leave your details below:
With this new range of voices, we invite you to embrace the newfound diversity and quality our platform offers. Explore, experiment, and elevate your stories to new heights. We can't wait to see what you come up with!
New to ElevenLabs?
Try the highest-rated text to speech and voice cloning software out there!