Book podcast
Turn your book into a multi-voice audio conversation, delivered as a single file.
The Book podcast reads a written exchange out loud, one line per turn, with a distinct voice and reading style for each speaker. Every line is synthesized separately, then everything is stitched into a single MP3 you can play on the page and download. That gives you a real spoken exchange to attach to your sales page, or an episode to feed your channel.
How it goes
Write your exchange
One line per turn, in the form "Name: what they say". A line without a name continues the previous turn, and a clickable example fills the field to show you the format.
Cast the voices
Pick a voice engine, then meet your characters in the cast list: each one is automatically given a different voice, which you can change. On the engine that supports reading styles, add a plain-language instruction per character, or one shared style for everyone.
Generate and grab the MP3
The summary shows the number of lines, the number of characters and the exact credit cost before you start. A progress bar tracks the generation, then the file appears with its player, a download button and its spot in "My dialogues".
What this feature does
A cast that fills itself in
As soon as a new name appears in your text, the character receives a free voice, different from the ones already taken. You then fine-tune every assignment as you like.
One reading style per speaker
On the engine that supports styles, each character can get their own plain-language instruction, such as an elderly, gentle voice. A shared style covers characters without one, and failing that, the style saved on your account applies.
Your own voice in the cast
On the engines that support cloning, you clone a voice without leaving the page from an MP3 or WAV sample, 15 seconds minimum recommended. The cloned voice joins the cast and stays reusable everywhere else.
The cost known before you start
The summary shows the exact total in credits, computed on the length of each line for the engine you chose, from 6 to 20 credits per 1,000 characters.
A single file delivered
Every line is read by its own voice, then everything is assembled into one MP3. You play it right on the page and download it with one button.
Your dialogues kept for you
Each generation lands in "My dialogues" with its audio, its text and its date. Come back whenever you want, and remove whatever you no longer need.
Three situations where it helps
An audio teaser on the sales page
Camille sells a guide about changing careers. Instead of another written summary, she drafts a ten-line exchange between a curious reader and a narrator who answers with the book's content. She assigns two distinct voices, runs the generation and drops the MP3 onto her sales page. Visitors hear the book's tone before they buy.
A dialogue episode for YouTube
Julien runs a channel about time management and has just finished his ebook. He writes a conversation between two characters, one skeptical, one convinced, each with their own reading style. The assembled file becomes his soundtrack: he adds a still image and publishes the episode. His book now has an audio format that runs without him.
Role-play scenes for a training course
Aminata trains online sellers and pairs every module with a digital book. To bring a chapter on customer service to life, she writes three short dialogues between a shop owner and a difficult customer. Each role keeps the same voice from one dialogue to the next, so her students listen to real situations instead of reading scripts.
Who it helps
Common questions
How much does a dialogue cost?
The price depends on the voice engine: 6, 10 or 20 credits per 1,000 characters, with a minimum of 1 credit per line. The exact total appears under your text before you start, so there are no surprises at billing time.
What file do I get, and in which format?
A single MP3 that assembles every line in order. You can play it on the page with the built-in player and download it in one click.
Can I use my own voice?
Yes, on the engines that support cloning. You upload an MP3 or WAV sample, 15 seconds minimum recommended, for 10 or 300 credits depending on the engine, with the cost shown in the panel. A certification is required for every clone: the voice must be yours, or cloned with the person's explicit permission.
How many characters can speak?
Up to 5 voices in a single dialogue. Each character keeps the same voice and style from start to finish.
Can I edit the dialogue after generation?
The delivered file cannot be edited afterwards. To change a line, fix your text and run the generation again, which is billed normally. Your previous versions stay in "My dialogues".
What happens if I stop mid-generation?
Stopping means you stop waiting: synthesis has already started on the provider's side, so the credits spent are not refunded. If the generation finishes anyway, the result shows up in "My dialogues".
Fifty credits free when you sign up
No card required. A browser is enough, on desktop or on your phone.
Create my free account