Text to Speech Agents Music Speech to Text Voice Cloning More

Studio

Create multi-chapter audiobooks and podcasts with AI voices. Assign different voices per chapter, manage pronunciation, and export complete projects.

Sign Up Free

New Project

Chapters

Draft
0 words · 0 characters
0:00

No chapters yet. Click \

Timeline

Generated chapters will appear here as a timeline. Generate individual chapters or click \

0:00
Generating chapter 1 of 3... 0%

Project Settings

0s 10s

Pronunciation Dictionary

Example: "TTS" → "tee tee ess"
Word Pronunciation
No pronunciation rules yet. Add words above or upload a dictionary file.

Export

Stitch all chapters into a single audio file Download each chapter as a separate file (ZIP)
Generate all chapters before exporting

How It Works

Produce professional audiobooks and podcasts in four simple steps.

Step 1

Create Project

Start a new project and choose the type: Audiobook, Podcast, Voiceover, or Presentation. Name it and set your default voice and model.

Step 2

Add Chapters

Add chapters or sections to your project. Paste text for each chapter, track word counts, and drag to reorder sections.

Step 3

Assign Voices

Pick a different AI voice for each chapter. Use the default for consistency or assign unique voices for narrators and characters.

Step 4

Export Audiobook

Generate all chapters with one click, then export as a single stitched audiobook or download individual chapters as a ZIP archive.

Use Cases

Studio is built for long-form audio production across industries.

Audiobooks

Convert entire novels, non-fiction books, and short stories into professional audiobooks. Use multi-voice to distinguish narrators and characters. Export as a single file ready for distribution on Audible, Spotify, or Apple Books.

Podcasts

Script and produce podcast episodes with multiple AI hosts. Create interview-style shows, news roundups, or storytelling series. Assign different voices per speaker and export broadcast-ready audio with chapter markers.

E-Learning Courses

Build complete course audio from lesson scripts. Organize modules into chapters, use a consistent instructor voice throughout, and add pronunciation rules for technical terms. Batch-generate entire curricula.

Corporate Training

Produce training materials, onboarding audio, and compliance modules at scale. Maintain a consistent brand voice across departments. Update content by editing text and regenerating without re-recording.

Documentation

Convert technical documentation, user guides, and manuals into audio format for accessibility. Use the pronunciation dictionary to handle acronyms, product names, and domain-specific terminology accurately.

Presentations

Generate narration tracks for slide decks and video presentations. Organize each slide as a chapter, assign timing per section, and export audio that syncs with your visual content for webinars and conferences.

Studio Features

Everything you need for professional long-form audio production.

Multi-Voice

Assign different AI voices to each chapter or section. Use one voice for narration and others for character dialog. Switch between 100+ voices across 24+ models for the perfect cast.

Chapter Management

Add, remove, and reorder chapters with drag-and-drop. Each section has its own text editor with word and character counts. Generate chapters individually or all at once.

Pronunciation Dictionary

Define custom pronunciation rules for names, acronyms, and technical terms. Upload a .txt or .pls dictionary file, or add word-pronunciation pairs manually to ensure accuracy.

One-Click Export

Export your entire project as a single stitched audio file with configurable chapter breaks, or download all chapters as individual files in a ZIP archive. MP3 or WAV output.

Frequently Asked Questions

Studio is a long-form audio production workspace. Create multi-chapter audiobooks, podcasts, or voiceover projects. Assign different voices to different sections, manage pronunciation dictionaries, and export as a single stitched audio file.

Each chapter or section can have a different voice assigned. For example, an audiobook can have a narrator voice for descriptions and different character voices for dialogue. You assign voices per section in the project editor.

A pronunciation dictionary lets you define how specific words should be spoken. Upload a .txt or .pls file with word-pronunciation pairs, or add them manually. Useful for character names, brand names, acronyms, and technical terms that AI might mispronounce.

Yes. Each chapter generates independently. If you need to fix a paragraph, just regenerate that section. The rest of your project stays intact. This saves time and credits on long projects.

Export your complete project as a single MP3 or WAV file with all chapters stitched together. You can also export individual chapters as separate files or download everything as a ZIP archive.

There is no hard limit on project length. Each chapter can be up to 50,000 characters. You can have unlimited chapters. Full-length novels (80,000+ words) are fully supported.

Yes. In project settings, you can set the chapter break duration — the silence inserted between chapters in the final export. Default is 2 seconds, adjustable from 0 to 10 seconds.

The core TTS API supports generating speech for individual sections. For full project management (chapters, voice assignment, stitching), use the web Studio interface. API-based project management is on the roadmap.

Using Kokoro (free tier), audiobook production costs 0 credits. A 60,000-word novel is approximately 360,000 characters. With standard-tier models (2 credits/1K chars), that would cost about 720 credits ($25-30).

Team collaboration is coming soon. Currently, projects are tied to individual accounts. The upcoming Teams feature will allow shared projects, team API keys, and usage dashboards.

Yes. You can use SSML tags in your text for fine-grained control over pronunciation, pauses, emphasis, and prosody. Combined with the pronunciation dictionary, you have complete control over how every word is spoken.

Yes. Upload a TXT, DOCX, or EPUB file and Studio will automatically split it into chapters. You can then assign voices, edit text, and generate audio for each chapter independently.
5.0/5 (1)

Create Your First Project

Build professional audiobooks and podcasts with AI voices. Multi-chapter support, multiple voices, pronunciation control.

Sign Up Free View Pricing