Studio, ElevenLabs’ AI longform text-to-audio editor for creators and storytellers is now free for everyone! Create audiobooks, voiceovers, and podcasts with new upgrades like pacing control, auto-assigned voices, and GenFM for AI-driven podcast creation.
Whether you're creating audiobooks, podcasts, or voiceovers, Studio makes it seamless with powerful new upgrades:
Pacing Control – Add precise pauses for natural speech flow.
Auto-Assignment of Voices – Instantly assign different voices to characters in your script.
GenFM Podcast Creation – Turn any document or URL into an AI-generated podcast-style discussion.
Free users can create, edit and export up to three projects in Studio. If you have a paid subscription, there are no limits on how many projects you can make.
Congratulations on the launch of ElevenLabs Studio! This addresses the challenge creators face in producing high-quality audio content.
How does ElevenLabs ensure the naturalness of AI-generated voices, particularly with features like pacing control and auto-assigned voices for different genres?
[Using Problem-solving tone]
Love how ElevenLabs Studio is addressing the time-consuming nature of audio content creation, especially for independent creators who struggle with consistent voice production and pacing.
Question: How does the GenFM feature determine the optimal conversation flow and speaker transitions when automatically generating podcast-style discussions from a single input text?
[Professional tone]
Congratulations on launching ElevenLabs Studio and making it accessible to all creators. As someone particularly interested in audio content creation, I'm curious about your approach to voice consistency across long-form content - how do you ensure the AI maintains natural intonation and emotional flow throughout extended narratives?
Woohoo! FlaiChat (a multilingual chat app) is currently using ElevenLabs as one of its providers to support Voice Translations.
Imagine hearing your Peruvian grandmother tell you all about her day in English, using her actual voice. It'd be amazing if you could support accent injection, so that some of that charm of non-native speaker personality can be preserved. And of course, would love to see your multilingual voices support Cantonese Chinese one day.
Congrats on this launch, love the customizability for content creators you're supporting.
I just tried ElevenLabs' Studio, and I have to say, this is a huge step forward for AI-powered audio creation. What really stood out to me is how effortless it is to use—the interface is clean, intuitive, and makes the whole process of turning text into high-quality audio feel seamless. No steep learning curve, no complicated settings—just a smooth, user-friendly experience.
The biggest highlight for me? The voices. They sound incredibly natural, which is something I’ve found lacking in a lot of AI-generated audio tools. Whether it’s for audiobooks, podcasts, or voiceovers, the quality is so good that it feels like working with a professional narrator. Plus, the new features like pacing control and auto-assigned voices make customization super easy, and GenFM’s AI-driven podcast creation adds another layer of creativity.
The fact that Studio is now free for everyone is a game-changer. It opens up so many possibilities for storytellers, content creators, and anyone who wants to experiment with AI-powered audio. I’m really excited to see where ElevenLabs takes this next!
Eleven Labs is truly living up to their $3b valuation :)
The enterprise potential of this AI audio technology will be immense. Imagine all corporate video's voice overs and training videos etc.. huge potential.
The team ships faaaaassssssst. Damn! Amazing update as usual. I'll give this one a try
Editing and generating long-form audio is very exciting. We often accumulate hundreds of hours of customer/employee interviews, any suggestion how to sample smartly from them?
