01
Book pages and textbooks
Photograph the pages you were assigned and listen to them on the way to class.
Image to Speech
Image to Speech and Picture to Speech Converter
Upload a photo, screenshot or scanned page and the text in it is read out in reading order, without headers or page numbers. Check the words, fix anything that's off, pick one of 30 voices, then listen here or download an MP3. This picture to speech tool reads the words in your image; it doesn't make the people in a photo talk.
How it works
How to Convert a Picture to Speech in Three Steps
Step 1
Upload your images
Drop in photos, screenshots or scanned pages: JPG, PNG, WebP or HEIC, up to 50 at once. A PDF works too. Each image is read as one page, and headers and page numbers are left out.
Step 2
Check the text
Read exactly what will be spoken. Fix a word the camera blurred, delete a caption you don't need, or untick a part. You only pay for the text you keep.
Step 3
Pick a voice and listen
Choose one of 30 voices, set the tone and pace, and generate. Play it right here, or download the MP3 on a paid plan.
What you get
Read the Text in Any Picture Aloud
Image to text to speech in one place: the words in your photo are recognized, shown to you to check, then spoken by a natural voice. Nothing to copy between an OCR app and a reader.
Read Text From an Image Aloud
Upload a picture, generate the audio and press play to hear the text read out loud, on a computer or a phone, with nothing to install. The text is read in reading order, and headers and page numbers are left out. The audio stays in your history after you close the tab.
OCR Text to Speech Without a Separate OCR Step
Photo to speech works with book pages taken at an angle, screenshots of articles and chats, scanned letters and phone pictures of a whiteboard. The text is read straight from the image. Neat handwriting often comes through, but it isn't guaranteed, so check those words before you generate.
Check the Text Before You Pay for Audio
Reading costs 5 credits an image, and those credits come back if reading fails. You get the text to look over: fix a name, delete a menu price you don't need to hear, and you're charged for audio only on the characters you keep.
Picture to Speech in 30 Voices
Pick from 30 natural AI voices, then set the tone and pace: calm for study notes, slower when you're learning a language and want to hear every word. The voice follows the language the text is written in, across 130+ languages, so there's no language menu to set.
Photo to Audio You Can Keep
This is image to audio and picture to audio for the words you photograph: each part downloads as an MP3 or WAV for your phone, your commute or someone you want to send it to, or all at once as a ZIP. Listening is free; downloads come with paid plans.
Up to 50 Images at Once
Photograph a whole chapter, a stack of handouts or every page of a letter, and upload them together. They're read as one text you can check in one place, split into parts, and each part becomes its own MP3.
Use cases
What People Turn Into Speech
Picture to speech for anything with words on it that you'd rather hear than read.
02
Handouts and worksheets
Turn a printed sheet from class or work into audio you can replay.
03
Screenshots
Articles, long messages and posts you saved as images, read aloud.
04
Menus and signs
Snap a menu, a notice or a label and hear what it says.
05
Scanned letters
Old letters and paper mail you've scanned, read back in a clear voice.
06
Reading support
Listening helps with dyslexia, low vision or tired eyes, when small print is hard to read.
07
Language learning
Hear how a page from your textbook sounds, at a slower pace if you need it.
08
Notes for the commute
Photograph your notes or a whiteboard and listen on the train or in the car.
More text to speech
Other Ways to Listen
FAQ
Image to Speech Questions
Upload one or more images and wait while the text is read, about two seconds an image. Check the text, choose a voice, tone and pace, then press Generate audio. Play it on this page, or download the MP3 on a paid plan.
Here, yes. Image to speech, picture to speech, photo to speech and image to voice all mean the same thing on this page: the text in your picture is recognized and read aloud by a voice.
Reading an image into text costs 5 credits per image, and those credits come back if reading fails. Generating audio costs 5 credits per 100 characters, and free accounts get 120 credits a month. Listening on this page is free; downloading MP3 or WAV comes with paid plans.
A full book page is about 2,000 characters, so about 100 credits of audio plus 5 credits to read it. A menu, sign or screenshot is usually much shorter. Your cost is shown before you generate.
No. This tool reads the words that appear in your image. Talking photo tools animate a face in a picture so it looks like it's speaking; that's a different kind of tool.
Yes. Recognizing the text (OCR) and reading it aloud happen in one place, so there's no separate OCR app to run first. You see the recognized text before any audio is made.
Yes. Screenshot to speech works well for articles, chats and posts, since the text is usually sharp. Menus, buttons and other app clutter are worth deleting from the text before you generate.
Often, if it's neat. Messy or faint handwriting can come out with mistakes, which is why you see and can fix the text before it becomes audio.
JPG, PNG, WebP and HEIC images, up to 50 at once and 30 MB each, or a single PDF of up to 500 pages and 100 MB. For long PDFs and books, PDF to Audio gives you one MP3 per chapter.
Yes. You get the text back first, and you can change or delete anything, or untick whole parts. Audio is charged only for what you keep.
Yes, on a paid plan. Each part downloads as MP3 or WAV, or you can get them all at once as a ZIP. Listening on this page is free.
More than 130, including English, Spanish, French, German, Japanese, Korean and Chinese. You don't choose one: the voice reads whatever language the text in your image is written in, which also makes it useful for hearing how a page in a new language sounds.
Many people find listening easier than reading small or dense print. Upload a picture of the page and listen at a slow or normal pace. It reads the images you upload; it isn't a screen reader for your whole device.
Your images are deleted as soon as they've been read. The text stays in your account so you can edit and generate, until you delete it.
Hear the Text in Your Next Photo
Read an image aloud in three steps: upload it, check the text and listen. Reading costs 5 credits an image, refunded if it fails.