How to turn text into speech with a natural voice
Voicence turns text into speech on your phone: write or paste the text, import a document, take a photo of a page or use the link to an article, pick a narrator and listen. The audio is saved as a recording, with the transcript synced word by word.
Free to start. For Android and iPhone.
Step by step
-
Open Text to audio
Tap the record button in the middle of the app's bottom bar and choose Text to audio.
-
Bring in your text
Write, paste what you copied, import a document, take a photo of a page or paste the link to an article.
-
Review before you create
Fix anything you need. Above the text, the app shows the character count, the estimated length of the audio and the cost in coins.
-
Pick a narrator
The language is picked from your text. Tap play to hear each narrator's sample, then tap Use this voice.
-
Confirm and listen
Check the length and the cost and tap Confirm and generate. The audio is ready in moments: give it a name and start listening.
Where your text can come from
You don't need to type anything if the text already exists somewhere else. These are the ways to bring it into the app:
- Write or paste: type from scratch or paste what you copied from another app.
- Document: PDF, Word (DOCX), ePub, PowerPoint (PPTX), ODT, TXT, Markdown, RTF and HTML. A scanned PDF, which is only images, goes through Photo or scan.
- Photo or scan: the app reads the text in book pages, slides and notes, with the camera or up to 10 photos from your gallery.
- Link to an article: paste the address and the app extracts the main text of the page.
- Share from another app: send text, a link or a file to Voicence from the share menu on Android or iPhone.
Natural-sounding narrators in over 50 languages
The voices are generated by AI and sound like a person reading, with pauses and intonation. The app detects the language of the text and opens the narrators for that language; you can switch languages at the top of the screen.
Each narrator has a name, a gender and a style, such as calm, warm, energetic, serious, deep or light. Tap play to hear a sample before you choose. English has narrators from the US, the UK, Australia and India.
The audio becomes a full recording
Once it's created, the audio shows up in your list with the AI voice badge and works like any other recording. The transcript is already there and synced: as the audio plays, each word is highlighted in the text.
That turns the same text into study material: you can get the summary, quiz, flashcards and mind map, translate it and export a PDF.
What it costs
Each minute of audio costs 1 coin. Before you create it, the app shows the estimated length, the cost and the balance you'll have left. If something goes wrong, your coins are refunded.
On the free plan each audio can be up to 10 minutes, and a short ad plays before it's created. If your text is longer, you can create just the first 10 minutes or go Premium, where each audio can be up to 120 minutes.
What people use it for
Listening instead of reading helps in many situations:
- Listening to class notes, summaries and study texts on the bus, at the gym or before an exam.
- Listening to articles and news instead of reading them on a screen.
- Turning PDFs and ePub books into audio you can listen to at your own pace.
- Proofreading something you wrote by hearing how it sounds out loud.
- Hearing how a text in another language is pronounced.
Frequently asked questions
Is text to speech free?
You can use it on the free plan: each minute of audio costs 1 coin, and each audio can be up to 10 minutes. You earn coins by watching ads or buy them in the app. With Premium each audio can be up to 120 minutes.
Can I turn a PDF into audio?
Yes. Import the PDF and the app extracts the text so you can review it and listen. If the PDF is scanned, with images only, use Photo or scan, which reads the text from the pages.
Which languages have narrators?
Over 50 languages, including English, Spanish, Portuguese, French, German, Italian, Japanese, Korean, Chinese, Arabic and Hindi.
Do I need an internet connection?
Yes. The text is sent to the server, where the audio is created, and comes back to the app ready to play.