Customer stories
Storytel
STUDIO
Structure, edit, and generate long-form audio with precision
Your comprehensive workflow for turning books into audiobooks and scripts into podcasts
Seth Godin
HarperCollins
Perplexity
Storytel
ElevenLabs
Multi-format file support
Initialize projects from a number of supported file formats, including EPUB, TXT, PDF, HTML; or pull directly from a URL
Expansive voice library
Find the perfect voice for your story. Choose from thousands of voices in the Voice Library or use Voice Design to create new ones. Adjust age, accent, delivery speed and voice settings to match your content perfectly, or for a personalized touch use your PVC
Structure your narrative
Format your text with our comprehensive editor. Add multiple chapters, assign unique voices to different sections, regenerate and download select phrases, and lock completed sections for better organization. Craft your narrative and connect with listeners worldwide
Emotional range & context
Our model responds to emotional cues and adapts its delivery to match both the content and the wider context. This allows our AI voices to achieve a high emotional range while avoiding logical mistakes.
Automatic quality checks
Each time you generate audio, we check for mispronunciations and unwanted artifacts. If we find any issues, the system automatically regenerates the audio at no extra cost
Access a full set of advanced features
Enjoy both the creative freedom and the hands-on control over your content with AI
Multilingual voices
Bring your characters to life across 32 languages. Choose tones and accents to enhance the narrative
Speaker assignment
Assign specific voices to selected text fragments, enhancing immersion and character depth
Fragment editing
Edit, refine and regenerate smaller fragments within your project until they feel right
See how creators and businesses are leveraging AI speech narration
HarperCollins Publishers
Customer stories
Leanna Morgan
HarperCollins Publishers
Customer stories
Leanna Morgan
Trusted by leading publishing and media companies
Frequently asked questions
Studio is our end-to-end workflow for producing audiobooks and other long-form audio content easily and with precision. It helps you structure, navigate, and voice your project, and it also provides advanced options such assigning specific text fragments to particular speakers or re-generating fragments inside bigger audio segments.
Absolutely, Studio is fully integrated with our Multilingual model and supports 32 languages. What's more, it automatically recognizes and accurately voices mixed-language text.
Yes, Studio lets you assign different speakers to specific text fragments, ensuring each of your story's characters has a unique voice.
Narrator supports EPUB, PDF, TXT, HTML files, and you can also initialize your project from a URL.
Studio works seamlessly with our range of tools, including Voice Library, Voice Design, our Multilingual models, and Professional Voice Cloning.
Explore our cutting-edge AI audio platform
Translate audio and video while preserving the emotion, timing, tone and unique characteristics of each speaker
Automate video voiceovers, ad reads, podcasts, and more, in your own voice
Create custom sound effects, instrumental tracks, and ambient audio with our powerful AI sound effect generator.
Our AI text to speech technology delivers thousands of high-quality, human-like voices in 70+ languages. Whether you’re looking for a free text to speech solution or a premium voice AI generator for commercial projects, our TTS tools & APIs can meet your needs