Open this writing studio
Edit Audiobook Voices Book Details Cover Images Song Export
Book Details Total chapters: 0 Total words: 0
Total voice generation costs: $0.00
Total image generation costs: $0.00
Total Production Cost: $0.0000
Cost Logs Storage
Chapter 1
Remove
Generate A Book Cover Your generated cover will appear here.
This image was created using the following description:
Generate A Song Song title Describe your song Lyrics (optional) Generate Song Generate Instrumental
Your generated song will appear here.
Take your story with you. Audiobook voice Download the whole book as one MP3 using each chapter’s saved audio and original voice. Generate complete audio for every chapter in Edit Audiobook before exporting.
Cancel audiobook Finish each chapter and add a book title and author name to download EPUB.
Download EPUB Download Audiobook Save draft file Open draft
Add AI Voice Saved Voices Back to chapter
English German French Spanish All genders Male Female Neutral All ages Young Teenager Middle aged Old Very old All styles Narrator Social media Sexy Computer All accents British Irish American Scottish Search
How To Use Close Enter your book title and author name. Add a synopsis if you want, and choose your spoken language. Name your first chapter. Click inside its text box to choose where new words should go. Click Start Dictation and allow microphone access. Speak naturally; your recording is transcribed when you click Stop Dictation. Click Stop Dictation to transcribe, format and read back your new recording. Start Dictation begins another recording at the cursor. Use New paragraph for paragraph breaks while continuing to dictate and Add chapter when ready for your next chapter. Click Download EPUB after all chapters contain text, or Save draft file at any time. New Book and My Books save your current draft before switching. Existing books from the previous app remain readable and editable.
Use a browser supporting microphone recording and open the app on HTTPS or localhost. Dictation sends your recording to OpenAI through the app server and requires internet access and a server API key. Typing remains available.
Recordings are limited to five minutes per session. Review the transcript after stopping. If transcription fails, your recording is downloaded for recovery.