Text to speech · Podcast

Turn any text into a podcast with two AI hosts.

Speecho turns an article, a chapter, your notes or a PDF, Word or EPUB file into a conversation between two AI hosts. They go through the text in its own order, asking and answering instead of reading it aloud, and stick to what it says. You get the script first: check it, edit any line, then voice it into one MP3 of about 5, 10 or 20 minutes.

Make a podcast from text →
Script from 16 credits · voicing priced per character · credits never expire · no subscription.

From a text to an episode in four steps

No recording, no microphone, and nothing is voiced until you have read the script.

chapter-3-podcast.mp3
2 hosts · about 10 min · Enhanced voices
Script ready
1Paste a text or open a file. An article, a chapter, lecture notes: anything from 300 to 60,000 characters. A PDF, Word or EPUB file opens in the text box first, read by your browser, so you see exactly what the hosts will work from. A longer text is cut at 60,000 characters, and the app tells you so.
2Set up the show. Pick a voice for each host, or let the app choose a woman and a man with voices suited to conversation. Names are optional. Choose about 5, 10 or 20 minutes, and the language of the script: the text's own or another one.
3Write and check the script. Writing it costs 15 credits for a script of up to 5 minutes, 25 for up to 10, 40 for up to 20, plus 1 credit per 3,000 characters of text, and the price is on the button. The script opens in the Dialogue editor. It was written by AI, so read it before voicing: fix a name or a number, cut a line, change a voice.
4Voice it into one MP3. The first ~5,000 characters are voiced first, so you hear the hosts before you pay for the rest. Download the whole episode as one MP3, and with Enhanced or Premium voices also as SRT or VTT subtitles.

Hear two voices together

Short dialogues written by hand and voiced in the Dialogue editor, the same place your podcast script is voiced. Premium voices.

Two friends and a forgotten booking

Voices: Anna (Jessica), Tom (Mark)

0:21
  1. Anna: Did you book the table for Friday?
  2. Tom: [sighs] I forgot. Again.
  3. Anna: Tom! It's my sister's birthday.
  4. Tom: I know, I know. I'll call them right now.
  5. Anna: [laughing] Too late. I booked it this morning.
  6. Tom: Then why did you ask?
  7. Anna: I wanted to see your face.

Two colleagues, in Japanese

Voices: さくら (Morioki), けんた (Hinata)

0:20
  1. さくら: 明日の会議、何時からだっけ?
  2. けんた: 十時からだよ。資料はもう送った?
  3. さくら: [sighs] まだ。今夜やるね。
  4. けんた: 手伝おうか? グラフなら得意だよ。
  5. さくら: 本当? じゃあお願い。お礼にコーヒーおごるね。
  6. けんた: [laughs] それなら二杯で。

What people turn into a podcast

Anything you would rather hear than read.

Study material

A week of reading and no time to sit down with it.

Now: each chapter talked through on the bus, point by point, in the chapter's own order.

Long articles and reports

Saved articles pile up, and a 30-page report waits for a quiet afternoon.

Now: two hosts walk through the argument while you cook, drive or walk.

Newsletters and blog posts

Readers ask for an audio version, and recording one every week takes an afternoon.

Now: an episode made from the post you already wrote, checked and edited before it goes out.

Team docs and training

A policy update or an onboarding guide that nobody reads to the end.

Now: a short episode built only from the document, for people to play on the way to work.

A text in another language

The source is in English, and your listeners speak Spanish.

Now: choose the script language, and the hosts discuss the text in it.

A first draft of an episode

A two-host script that starts from a blank page takes hours.

Now: a script built from your notes, rewritten line by line in the editor, then voiced.

One episode at a glance

What an episode costs

Two separate charges: the script, by its length and the length of your text, and the voicing, by the length of the script. Both show on the button before anything is charged.

Script15 credits up to 5 minutes, 25 up to 10, 40 up to 20, plus 1 credit per 3,000 characters of text. A 6,000-character article costs 17 credits at 5 minutes or 27 at 10, a 30,000-character chapter 35 at 10 minutes, a 60,000-character document 60 at 20. A short text is not stretched to the length you pick and is charged for the script it really gets.
VoicingPriced like any dialogue, per 1,000 characters. 50 credits on Standard, 110 on Enhanced, 160 on Premium. Two hosts cost no more than one voice.
10 minutesAbout 1,500 words, about 9,000 characters. About 450 credits on Standard, 990 on Enhanced, 1,440 on Premium. A 10-minute Enhanced episode and its script fit in the $5 pack.
Packs$5 = 2,400 credits, $10 = 6,000, $25 = 16,800, $50 = 36,000. Credits never expire, there is no subscription, and there is a 14-day refund.

A long episode is voiced in portions: you hear the first ~5,000 characters before paying for the rest. All prices on the pricing page →

Frequently asked questions

How do I turn a text into a podcast?

Open Text to speech in Speecho and press “Make a podcast from text”. Paste a text or open a PDF, Word or EPUB file, pick the two hosts, a length of about 5, 10 or 20 minutes and a language, and write the script. It opens in the Dialogue editor, where you check it, change lines or voices, and voice it into one MP3.

How much does an AI podcast cost?

Two parts. The script costs 15, 25 or 40 credits for about 5, 10 or 20 minutes, plus 1 credit per 3,000 characters of your text: 16 to 60 in all. Voicing costs what any dialogue costs: 50, 110 or 160 credits per 1,000 characters on Standard, Enhanced or Premium voices. A 10-minute episode is about 9,000 characters: about 450 credits on Standard or 990 on Enhanced. Packs start at $5 for 2,400 credits; credits never expire and there is no subscription.

How long is the podcast, and how long can my text be?

You choose about 5, 10 or 20 minutes; the length is approximate, so an episode can come out a little shorter or longer. The text can be 300 to 60,000 characters. A longer text is cut at 60,000 characters, the script covers only its beginning, and the app tells you so.

Which languages can the podcast be in?

The script is written in the language of your text, or in another one you choose: an English article can become an episode in Spanish. The voices come in three quality tiers and many languages, and you can give each host any voice you like.

Will the hosts make things up?

They are told to stick to what the text says, in its order, and to discuss it rather than add to it. The script is still written by AI and can get a detail wrong, a name, a number or a nuance, so read it in the editor before you voice it. Editing lines is free: you pay for voicing only when you start it.

Can I edit the script before it is voiced?

Yes. It opens in the Dialogue editor as lines for each host. Rewrite or delete lines, add your own, rename the hosts or give them other voices, and hear every voice free before you voice anything.

Which files can I use?

Paste any text, or open a PDF, Word (DOCX) or EPUB file. The file opens in the text box first and is read by your browser, so you can see the text and cut what you do not need before the script is written.

Can I use the podcast commercially?

Yes. Generation runs on the paid commercial API tiers of our voice providers, whose terms permit commercial use of the generated audio. You are responsible for the content of the script and for having the right to use the text you start from.

Other ways to turn text into audio

Hear your next read instead.

Paste a text, check the script, voice it. A script costs from 16 credits, and you hear the start of the episode before you pay for the rest.

Make a podcast →